Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2022 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4218. Min Range: -5.4218
Max Act: 5.4218. Min Act: -0.1700
Data Index: 4767374 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4218. Min Range: -5.4218
Max Act: 5.3593. Min Act: -0.1700
Data Index: 8335048 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4218. Min Range: -5.4218
Max Act: 5.3593. Min Act: -0.1700
Data Index: 4058046 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4218. Min Range: -5.4218
Max Act: 5.3906. Min Act: -0.1700
Data Index: 4859548 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4218. Min Range: -5.4218
Max Act: 5.3906. Min Act: -0.1700
Data Index: 8393399 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4218. Min Range: -5.4218
Max Act: 5.3281. Min Act: -0.1700
Data Index: 282257 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4218. Min Range: -5.4218
Max Act: 5.3281. Min Act: -0.1700
Data Index: 3547127 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4218. Min Range: -5.4218
Max Act: 5.2968. Min Act: -0.1700
Data Index: 1455705 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4218. Min Range: -5.4218
Max Act: 5.2968. Min Act: -0.1700
Data Index: 2860853 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4218. Min Range: -5.4218
Max Act: 5.2968. Min Act: -0.1700
Data Index: 3578170 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4218. Min Range: -5.4218
Max Act: 5.2968. Min Act: -0.1700
Data Index: 5148496 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4218. Min Range: -5.4218
Max Act: 5.2968. Min Act: -0.1700
Data Index: 5245954 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4218. Min Range: -5.4218
Max Act: 5.2968. Min Act: -0.1700
Data Index: 5834544 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4218. Min Range: -5.4218
Max Act: 5.2656. Min Act: -0.1700
Data Index: 1159481 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4218. Min Range: -5.4218
Max Act: 5.2656. Min Act: -0.1700
Data Index: 7946915 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4218. Min Range: -5.4218
Max Act: 5.2656. Min Act: -0.1700
Data Index: 2708971 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4218. Min Range: -5.4218
Max Act: 5.2343. Min Act: -0.1700
Data Index: 3047519 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4218. Min Range: -5.4218
Max Act: 5.2343. Min Act: -0.1700
Data Index: 2057324 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4218. Min Range: -5.4218
Max Act: 5.2343. Min Act: -0.1700
Data Index: 2205408 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4218. Min Range: -5.4218
Max Act: 5.2343. Min Act: -0.1700
Data Index: 5622926 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19