Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3063 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5070. Min Range: -6.5070
Max Act: 6.5070. Min Act: -0.1700
Data Index: 948732 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5070. Min Range: -6.5070
Max Act: 6.3820. Min Act: -0.1700
Data Index: 5234901 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5070. Min Range: -6.5070
Max Act: 6.3507. Min Act: -0.1700
Data Index: 1966480 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5070. Min Range: -6.5070
Max Act: 6.3507. Min Act: -0.1700
Data Index: 7510923 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5070. Min Range: -6.5070
Max Act: 6.2882. Min Act: -0.1700
Data Index: 7608975 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5070. Min Range: -6.5070
Max Act: 6.3195. Min Act: -0.1700
Data Index: 5062198 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5070. Min Range: -6.5070
Max Act: 6.3195. Min Act: -0.1700
Data Index: 658441 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5070. Min Range: -6.5070
Max Act: 6.2882. Min Act: -0.1700
Data Index: 627320 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5070. Min Range: -6.5070
Max Act: 6.2882. Min Act: -0.1700
Data Index: 3836933 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5070. Min Range: -6.5070
Max Act: 6.2570. Min Act: -0.1700
Data Index: 5089588 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5070. Min Range: -6.5070
Max Act: 6.2257. Min Act: -0.1700
Data Index: 6178123 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5070. Min Range: -6.5070
Max Act: 6.2257. Min Act: -0.1700
Data Index: 4767363 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5070. Min Range: -6.5070
Max Act: 6.1945. Min Act: -0.1700
Data Index: 2786702 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5070. Min Range: -6.5070
Max Act: 6.2257. Min Act: -0.1700
Data Index: 3300695 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5070. Min Range: -6.5070
Max Act: 6.1945. Min Act: -0.1700
Data Index: 6110860 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5070. Min Range: -6.5070
Max Act: 6.2257. Min Act: -0.1700
Data Index: 4322839 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5070. Min Range: -6.5070
Max Act: 6.1632. Min Act: -0.1700
Data Index: 631302 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5070. Min Range: -6.5070
Max Act: 6.1632. Min Act: -0.1700
Data Index: 8293412 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5070. Min Range: -6.5070
Max Act: 6.1320. Min Act: -0.1700
Data Index: 2109409 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5070. Min Range: -6.5070
Max Act: 6.1320. Min Act: -0.1700
Data Index: 1587531 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19