Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6122. Min Range: -5.6122
Max Act: 5.6122. Min Act: -0.1700
Data Index: 189473 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6122. Min Range: -5.6122
Max Act: 5.6122. Min Act: -0.1700
Data Index: 2725193 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6122. Min Range: -5.6122
Max Act: 5.4872. Min Act: -0.1700
Data Index: 8680689 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6122. Min Range: -5.6122
Max Act: 5.4247. Min Act: -0.1700
Data Index: 6068415 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6122. Min Range: -5.6122
Max Act: 5.4247. Min Act: -0.1700
Data Index: 5444863 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6122. Min Range: -5.6122
Max Act: 5.3935. Min Act: -0.1700
Data Index: 8276460 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6122. Min Range: -5.6122
Max Act: 5.3622. Min Act: -0.1700
Data Index: 7214507 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6122. Min Range: -5.6122
Max Act: 5.3622. Min Act: -0.1700
Data Index: 5732283 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6122. Min Range: -5.6122
Max Act: 5.2997. Min Act: -0.1700
Data Index: 5704266 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6122. Min Range: -5.6122
Max Act: 5.2997. Min Act: -0.1700
Data Index: 3844323 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6122. Min Range: -5.6122
Max Act: 5.3310. Min Act: -0.1700
Data Index: 2307681 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6122. Min Range: -5.6122
Max Act: 5.3310. Min Act: -0.1700
Data Index: 1097832 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6122. Min Range: -5.6122
Max Act: 5.3310. Min Act: -0.1700
Data Index: 2567867 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6122. Min Range: -5.6122
Max Act: 5.2997. Min Act: -0.1700
Data Index: 8471850 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6122. Min Range: -5.6122
Max Act: 5.2685. Min Act: -0.1700
Data Index: 6319676 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6122. Min Range: -5.6122
Max Act: 5.2685. Min Act: -0.1700
Data Index: 1093103 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6122. Min Range: -5.6122
Max Act: 5.2685. Min Act: -0.1700
Data Index: 1425761 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6122. Min Range: -5.6122
Max Act: 5.2685. Min Act: -0.1700
Data Index: 2471831 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6122. Min Range: -5.6122
Max Act: 5.2685. Min Act: -0.1700
Data Index: 1154366 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6122. Min Range: -5.6122
Max Act: 5.2372. Min Act: -0.1700
Data Index: 1505066 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19