Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5253 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0233. Min Range: -5.0233
Max Act: 5.0233. Min Act: -0.1700
Data Index: 2862290 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.8983. Min Act: -0.1700
Data Index: 4146269 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.6483. Min Act: -0.1700
Data Index: 3406946 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.6170. Min Act: -0.1700
Data Index: 3541448 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.5858. Min Act: -0.1700
Data Index: 2917472 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.5858. Min Act: -0.1700
Data Index: 4978958 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.6170. Min Act: -0.1700
Data Index: 4367576 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.5858. Min Act: -0.1700
Data Index: 5182854 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.5858. Min Act: -0.1700
Data Index: 2242407 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.5545. Min Act: -0.1700
Data Index: 1682737 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.5545. Min Act: -0.1700
Data Index: 414062 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.5545. Min Act: -0.1700
Data Index: 664972 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.4920. Min Act: -0.1700
Data Index: 5625540 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.5233. Min Act: -0.1700
Data Index: 30132 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.4920. Min Act: -0.1700
Data Index: 4210932 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.4920. Min Act: -0.1700
Data Index: 5419380 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.4920. Min Act: -0.1700
Data Index: 3849067 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.4920. Min Act: -0.1700
Data Index: 4075023 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.4920. Min Act: -0.1700
Data Index: 6011734 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0233. Min Range: -5.0233
Max Act: 4.4920. Min Act: -0.1700
Data Index: 6888579 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19