Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 56 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8603. Min Range: -5.8603
Max Act: 5.8603. Min Act: -0.1700
Data Index: 2775042 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8603. Min Range: -5.8603
Max Act: 5.8291. Min Act: -0.1700
Data Index: 4993460 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8603. Min Range: -5.8603
Max Act: 5.8291. Min Act: -0.1700
Data Index: 7008081 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8603. Min Range: -5.8603
Max Act: 5.8291. Min Act: -0.1700
Data Index: 4244903 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8603. Min Range: -5.8603
Max Act: 5.7978. Min Act: -0.1700
Data Index: 3675691 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8603. Min Range: -5.8603
Max Act: 5.7978. Min Act: -0.1700
Data Index: 5623752 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8603. Min Range: -5.8603
Max Act: 5.7978. Min Act: -0.1700
Data Index: 2354232 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8603. Min Range: -5.8603
Max Act: 5.7353. Min Act: -0.1700
Data Index: 116952 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8603. Min Range: -5.8603
Max Act: 5.7041. Min Act: -0.1700
Data Index: 5725496 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8603. Min Range: -5.8603
Max Act: 5.7041. Min Act: -0.1700
Data Index: 1694146 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8603. Min Range: -5.8603
Max Act: 5.7041. Min Act: -0.1700
Data Index: 4672356 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8603. Min Range: -5.8603
Max Act: 5.7041. Min Act: -0.1700
Data Index: 4429183 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8603. Min Range: -5.8603
Max Act: 5.6416. Min Act: -0.1700
Data Index: 6213760 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8603. Min Range: -5.8603
Max Act: 5.6416. Min Act: -0.1700
Data Index: 3077460 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8603. Min Range: -5.8603
Max Act: 5.5791. Min Act: -0.1700
Data Index: 905194 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8603. Min Range: -5.8603
Max Act: 5.5791. Min Act: -0.1700
Data Index: 3303569 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8603. Min Range: -5.8603
Max Act: 5.6103. Min Act: -0.1700
Data Index: 5700562 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8603. Min Range: -5.8603
Max Act: 5.6103. Min Act: -0.1700
Data Index: 6368491 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8603. Min Range: -5.8603
Max Act: 5.6103. Min Act: -0.1700
Data Index: 733809 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8603. Min Range: -5.8603
Max Act: 5.5791. Min Act: -0.1700
Data Index: 5476536 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19