Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1707 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3214. Min Range: -5.3214
Max Act: 5.3214. Min Act: -0.1700
Data Index: 4574881 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3214. Min Range: -5.3214
Max Act: 5.1339. Min Act: -0.1700
Data Index: 6773574 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3214. Min Range: -5.3214
Max Act: 5.1339. Min Act: -0.1700
Data Index: 6365915 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3214. Min Range: -5.3214
Max Act: 5.1339. Min Act: -0.1700
Data Index: 1015695 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3214. Min Range: -5.3214
Max Act: 5.1026. Min Act: -0.1700
Data Index: 6842892 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3214. Min Range: -5.3214
Max Act: 5.0401. Min Act: -0.1700
Data Index: 5194956 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3214. Min Range: -5.3214
Max Act: 5.0401. Min Act: -0.1700
Data Index: 6152672 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3214. Min Range: -5.3214
Max Act: 5.0401. Min Act: -0.1700
Data Index: 913452 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3214. Min Range: -5.3214
Max Act: 5.0089. Min Act: -0.1700
Data Index: 6059997 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3214. Min Range: -5.3214
Max Act: 5.0089. Min Act: -0.1700
Data Index: 7171285 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3214. Min Range: -5.3214
Max Act: 5.0089. Min Act: -0.1700
Data Index: 8417070 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3214. Min Range: -5.3214
Max Act: 4.9776. Min Act: -0.1700
Data Index: 5638743 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3214. Min Range: -5.3214
Max Act: 5.0089. Min Act: -0.1700
Data Index: 1650786 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3214. Min Range: -5.3214
Max Act: 5.0089. Min Act: -0.1700
Data Index: 371134 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3214. Min Range: -5.3214
Max Act: 4.9776. Min Act: -0.1700
Data Index: 4611562 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3214. Min Range: -5.3214
Max Act: 4.9464. Min Act: -0.1700
Data Index: 6701588 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3214. Min Range: -5.3214
Max Act: 4.8839. Min Act: -0.1700
Data Index: 5627070 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3214. Min Range: -5.3214
Max Act: 4.9151. Min Act: -0.1700
Data Index: 39608 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3214. Min Range: -5.3214
Max Act: 4.9151. Min Act: -0.1700
Data Index: 6478742 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3214. Min Range: -5.3214
Max Act: 4.8839. Min Act: -0.1700
Data Index: 3430523 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19