Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 757 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6518. Min Range: -6.6518
Max Act: 6.6518. Min Act: -0.1700
Data Index: 6622747 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6518. Min Range: -6.6518
Max Act: 6.6518. Min Act: -0.1700
Data Index: 5769240 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6518. Min Range: -6.6518
Max Act: 6.5581. Min Act: -0.1700
Data Index: 3098171 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6518. Min Range: -6.6518
Max Act: 6.5581. Min Act: -0.1700
Data Index: 1720143 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6518. Min Range: -6.6518
Max Act: 6.5268. Min Act: -0.1700
Data Index: 7673411 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6518. Min Range: -6.6518
Max Act: 6.4643. Min Act: -0.1700
Data Index: 4557503 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6518. Min Range: -6.6518
Max Act: 6.4331. Min Act: -0.1700
Data Index: 5307610 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6518. Min Range: -6.6518
Max Act: 6.4643. Min Act: -0.1700
Data Index: 6487122 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6518. Min Range: -6.6518
Max Act: 6.4331. Min Act: -0.1700
Data Index: 5243301 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6518. Min Range: -6.6518
Max Act: 6.3706. Min Act: -0.1700
Data Index: 2023130 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6518. Min Range: -6.6518
Max Act: 6.4018. Min Act: -0.1700
Data Index: 3259110 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6518. Min Range: -6.6518
Max Act: 6.3706. Min Act: -0.1700
Data Index: 1490166 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6518. Min Range: -6.6518
Max Act: 6.3706. Min Act: -0.1700
Data Index: 3257625 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6518. Min Range: -6.6518
Max Act: 6.3393. Min Act: -0.1700
Data Index: 4790212 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6518. Min Range: -6.6518
Max Act: 6.3081. Min Act: -0.1700
Data Index: 66065 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6518. Min Range: -6.6518
Max Act: 6.2768. Min Act: -0.1700
Data Index: 2442880 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6518. Min Range: -6.6518
Max Act: 6.2768. Min Act: -0.1700
Data Index: 7329488 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6518. Min Range: -6.6518
Max Act: 6.2768. Min Act: -0.1700
Data Index: 2645384 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6518. Min Range: -6.6518
Max Act: 6.2456. Min Act: -0.1700
Data Index: 7540212 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6518. Min Range: -6.6518
Max Act: 6.2143. Min Act: -0.1700
Data Index: 6612540 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19