Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4720 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.9862. Min Act: -0.1700
Data Index: 3356652 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.9237. Min Act: -0.1700
Data Index: 8066165 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.8925. Min Act: -0.1700
Data Index: 450401 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.8612. Min Act: -0.1700
Data Index: 6742374 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.8612. Min Act: -0.1700
Data Index: 1484946 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.7362. Min Act: -0.1700
Data Index: 4167165 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.7050. Min Act: -0.1700
Data Index: 8499976 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.6737. Min Act: -0.1700
Data Index: 5366892 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.7050. Min Act: -0.1700
Data Index: 303043 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.6737. Min Act: -0.1700
Data Index: 6106309 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.6737. Min Act: -0.1700
Data Index: 4514669 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.6737. Min Act: -0.1700
Data Index: 4007776 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.6425. Min Act: -0.1700
Data Index: 1368361 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.6425. Min Act: -0.1700
Data Index: 1882192 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.6112. Min Act: -0.1700
Data Index: 3145714 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.6425. Min Act: -0.1700
Data Index: 3521872 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.6112. Min Act: -0.1700
Data Index: 4227733 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.6112. Min Act: -0.1700
Data Index: 5558890 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.6112. Min Act: -0.1700
Data Index: 4694151 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.6112. Min Act: -0.1700
Data Index: 1176056 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19