Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3305 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.6042. Min Act: -0.1700
Data Index: 4091411 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.5105. Min Act: -0.1700
Data Index: 8035177 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.5105. Min Act: -0.1700
Data Index: 6610732 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.5105. Min Act: -0.1700
Data Index: 7406008 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.5105. Min Act: -0.1700
Data Index: 25365 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.5105. Min Act: -0.1700
Data Index: 275487 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.5105. Min Act: -0.1700
Data Index: 7653332 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.4167. Min Act: -0.1700
Data Index: 3227736 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.4167. Min Act: -0.1700
Data Index: 1599438 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.3855. Min Act: -0.1700
Data Index: 922451 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.3855. Min Act: -0.1700
Data Index: 4464021 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.3855. Min Act: -0.1700
Data Index: 2106502 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.3855. Min Act: -0.1700
Data Index: 3970542 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.3855. Min Act: -0.1700
Data Index: 6239090 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.3542. Min Act: -0.1700
Data Index: 2359576 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.3542. Min Act: -0.1700
Data Index: 5981126 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.3542. Min Act: -0.1700
Data Index: 25354 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.3542. Min Act: -0.1700
Data Index: 958114 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.3542. Min Act: -0.1700
Data Index: 3709505 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6042. Min Range: -5.6042
Max Act: 5.3542. Min Act: -0.1700
Data Index: 6293222 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19