Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2637 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.5571. Min Range: -11.5571
Max Act: 11.5571. Min Act: -0.1700
Data Index: 4473510 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5571. Min Range: -11.5571
Max Act: 11.5571. Min Act: -0.1700
Data Index: 2336597 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5571. Min Range: -11.5571
Max Act: 11.5571. Min Act: -0.1700
Data Index: 5891291 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5571. Min Range: -11.5571
Max Act: 11.4946. Min Act: -0.1700
Data Index: 2940026 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5571. Min Range: -11.5571
Max Act: 11.4946. Min Act: -0.1700
Data Index: 3482650 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5571. Min Range: -11.5571
Max Act: 11.4321. Min Act: -0.1700
Data Index: 141040 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5571. Min Range: -11.5571
Max Act: 11.4321. Min Act: -0.1700
Data Index: 508308 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5571. Min Range: -11.5571
Max Act: 11.3071. Min Act: -0.1700
Data Index: 5138856 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5571. Min Range: -11.5571
Max Act: 11.2446. Min Act: -0.1700
Data Index: 5140206 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5571. Min Range: -11.5571
Max Act: 11.2446. Min Act: -0.1700
Data Index: 7652899 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5571. Min Range: -11.5571
Max Act: 11.1821. Min Act: -0.1700
Data Index: 5018113 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5571. Min Range: -11.5571
Max Act: 11.1196. Min Act: -0.1700
Data Index: 1745655 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5571. Min Range: -11.5571
Max Act: 11.1196. Min Act: -0.1700
Data Index: 2859144 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5571. Min Range: -11.5571
Max Act: 11.1196. Min Act: -0.1700
Data Index: 2121647 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5571. Min Range: -11.5571
Max Act: 11.1196. Min Act: -0.1700
Data Index: 3864065 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5571. Min Range: -11.5571
Max Act: 11.0571. Min Act: -0.1700
Data Index: 2710041 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5571. Min Range: -11.5571
Max Act: 11.0571. Min Act: -0.1700
Data Index: 8789646 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5571. Min Range: -11.5571
Max Act: 11.0571. Min Act: -0.1700
Data Index: 3564845 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5571. Min Range: -11.5571
Max Act: 11.0571. Min Act: -0.1700
Data Index: 2161321 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5571. Min Range: -11.5571
Max Act: 10.9946. Min Act: -0.1700
Data Index: 4199923 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19