Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2754 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9897. Min Range: -5.9897
Max Act: 5.9897. Min Act: -0.1700
Data Index: 4465456 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9897. Min Range: -5.9897
Max Act: 5.9585. Min Act: -0.1700
Data Index: 6986512 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9897. Min Range: -5.9897
Max Act: 5.9272. Min Act: -0.1700
Data Index: 7628090 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9897. Min Range: -5.9897
Max Act: 5.9272. Min Act: -0.1700
Data Index: 218286 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9897. Min Range: -5.9897
Max Act: 5.8960. Min Act: -0.1700
Data Index: 8658799 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9897. Min Range: -5.9897
Max Act: 5.8647. Min Act: -0.1700
Data Index: 4457727 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9897. Min Range: -5.9897
Max Act: 5.8022. Min Act: -0.1700
Data Index: 3897259 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9897. Min Range: -5.9897
Max Act: 5.8022. Min Act: -0.1700
Data Index: 6702565 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9897. Min Range: -5.9897
Max Act: 5.7710. Min Act: -0.1700
Data Index: 7014533 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9897. Min Range: -5.9897
Max Act: 5.7397. Min Act: -0.1700
Data Index: 8704026 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9897. Min Range: -5.9897
Max Act: 5.7085. Min Act: -0.1700
Data Index: 2336137 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9897. Min Range: -5.9897
Max Act: 5.7085. Min Act: -0.1700
Data Index: 666414 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9897. Min Range: -5.9897
Max Act: 5.6772. Min Act: -0.1700
Data Index: 474827 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9897. Min Range: -5.9897
Max Act: 5.6772. Min Act: -0.1700
Data Index: 6352049 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9897. Min Range: -5.9897
Max Act: 5.6460. Min Act: -0.1700
Data Index: 2056460 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9897. Min Range: -5.9897
Max Act: 5.6772. Min Act: -0.1700
Data Index: 3353628 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9897. Min Range: -5.9897
Max Act: 5.6147. Min Act: -0.1700
Data Index: 4952958 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9897. Min Range: -5.9897
Max Act: 5.6772. Min Act: -0.1700
Data Index: 231975 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9897. Min Range: -5.9897
Max Act: 5.6460. Min Act: -0.1700
Data Index: 2509289 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9897. Min Range: -5.9897
Max Act: 5.6147. Min Act: -0.1700
Data Index: 3792350 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19