Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 822 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9223. Min Range: -9.9223
Max Act: 9.9223. Min Act: -0.1700
Data Index: 285915 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9223. Min Range: -9.9223
Max Act: 9.6723. Min Act: -0.1700
Data Index: 4494389 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9223. Min Range: -9.9223
Max Act: 9.7348. Min Act: -0.1700
Data Index: 5060610 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9223. Min Range: -9.9223
Max Act: 9.6098. Min Act: -0.1700
Data Index: 4882777 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9223. Min Range: -9.9223
Max Act: 9.6098. Min Act: -0.1700
Data Index: 6642760 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9223. Min Range: -9.9223
Max Act: 9.4848. Min Act: -0.1700
Data Index: 5957914 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9223. Min Range: -9.9223
Max Act: 9.4848. Min Act: -0.1700
Data Index: 237625 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9223. Min Range: -9.9223
Max Act: 9.4848. Min Act: -0.1700
Data Index: 5748016 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9223. Min Range: -9.9223
Max Act: 9.4848. Min Act: -0.1700
Data Index: 3116878 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9223. Min Range: -9.9223
Max Act: 9.4223. Min Act: -0.1700
Data Index: 3101141 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9223. Min Range: -9.9223
Max Act: 9.4223. Min Act: -0.1700
Data Index: 5375370 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9223. Min Range: -9.9223
Max Act: 9.4223. Min Act: -0.1700
Data Index: 4973619 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9223. Min Range: -9.9223
Max Act: 9.3598. Min Act: -0.1700
Data Index: 3529546 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9223. Min Range: -9.9223
Max Act: 9.3598. Min Act: -0.1700
Data Index: 8034450 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9223. Min Range: -9.9223
Max Act: 9.3598. Min Act: -0.1700
Data Index: 8034453 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9223. Min Range: -9.9223
Max Act: 9.2973. Min Act: -0.1700
Data Index: 8244468 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9223. Min Range: -9.9223
Max Act: 9.2973. Min Act: -0.1700
Data Index: 5051712 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9223. Min Range: -9.9223
Max Act: 9.2973. Min Act: -0.1700
Data Index: 3206470 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9223. Min Range: -9.9223
Max Act: 9.2973. Min Act: -0.1700
Data Index: 3101144 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9223. Min Range: -9.9223
Max Act: 9.2348. Min Act: -0.1700
Data Index: 3227752 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19