Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3540 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3630. Min Range: -6.3630
Max Act: 6.3630. Min Act: -0.1700
Data Index: 2377934 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3630. Min Range: -6.3630
Max Act: 6.0818. Min Act: -0.1700
Data Index: 1515707 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.9568. Min Act: -0.1700
Data Index: 4570774 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.8318. Min Act: -0.1700
Data Index: 6878051 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.8318. Min Act: -0.1700
Data Index: 58248 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.8318. Min Act: -0.1700
Data Index: 3328474 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.8318. Min Act: -0.1700
Data Index: 6264840 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.7693. Min Act: -0.1700
Data Index: 3232990 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.7693. Min Act: -0.1700
Data Index: 3699480 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.7693. Min Act: -0.1700
Data Index: 7843162 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.7380. Min Act: -0.1700
Data Index: 8393665 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.7068. Min Act: -0.1700
Data Index: 4480296 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.6755. Min Act: -0.1700
Data Index: 8224301 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.7068. Min Act: -0.1700
Data Index: 6878058 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.7068. Min Act: -0.1700
Data Index: 816894 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.6755. Min Act: -0.1700
Data Index: 5507030 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.6443. Min Act: -0.1700
Data Index: 7705394 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.6443. Min Act: -0.1700
Data Index: 7921063 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.6130. Min Act: -0.1700
Data Index: 262986 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3630. Min Range: -6.3630
Max Act: 5.5818. Min Act: -0.1700
Data Index: 1622556 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19