Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1446 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3353. Min Range: -6.3353
Max Act: 6.3353. Min Act: -0.1700
Data Index: 4586474 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3353. Min Range: -6.3353
Max Act: 6.3353. Min Act: -0.1700
Data Index: 4456855 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3353. Min Range: -6.3353
Max Act: 6.3041. Min Act: -0.1700
Data Index: 1226475 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3353. Min Range: -6.3353
Max Act: 6.3041. Min Act: -0.1700
Data Index: 3064409 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3353. Min Range: -6.3353
Max Act: 6.3041. Min Act: -0.1700
Data Index: 4026922 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3353. Min Range: -6.3353
Max Act: 6.2728. Min Act: -0.1700
Data Index: 1741094 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3353. Min Range: -6.3353
Max Act: 6.2728. Min Act: -0.1700
Data Index: 93761 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3353. Min Range: -6.3353
Max Act: 6.2728. Min Act: -0.1700
Data Index: 3408518 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3353. Min Range: -6.3353
Max Act: 6.2728. Min Act: -0.1700
Data Index: 5841980 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3353. Min Range: -6.3353
Max Act: 6.2416. Min Act: -0.1700
Data Index: 8093751 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3353. Min Range: -6.3353
Max Act: 6.2416. Min Act: -0.1700
Data Index: 3162738 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3353. Min Range: -6.3353
Max Act: 6.2103. Min Act: -0.1699
Data Index: 1020421 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3353. Min Range: -6.3353
Max Act: 6.2103. Min Act: -0.1700
Data Index: 7376136 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3353. Min Range: -6.3353
Max Act: 6.2103. Min Act: -0.1700
Data Index: 7308347 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3353. Min Range: -6.3353
Max Act: 6.2103. Min Act: -0.1700
Data Index: 7100613 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3353. Min Range: -6.3353
Max Act: 6.2103. Min Act: -0.1700
Data Index: 5558343 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3353. Min Range: -6.3353
Max Act: 6.2103. Min Act: -0.1700
Data Index: 860885 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3353. Min Range: -6.3353
Max Act: 6.2103. Min Act: -0.1700
Data Index: 307270 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3353. Min Range: -6.3353
Max Act: 6.2103. Min Act: -0.1700
Data Index: 833612 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3353. Min Range: -6.3353
Max Act: 6.2103. Min Act: -0.1700
Data Index: 188735 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19