Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3222 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7816. Min Range: -5.7816
Max Act: 5.7816. Min Act: -0.1699
Data Index: 2200545 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7816. Min Range: -5.7816
Max Act: 5.7503. Min Act: -0.1700
Data Index: 6305242 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7816. Min Range: -5.7816
Max Act: 5.6566. Min Act: -0.1700
Data Index: 1784508 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7816. Min Range: -5.7816
Max Act: 5.6566. Min Act: -0.1700
Data Index: 4575211 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7816. Min Range: -5.7816
Max Act: 5.6253. Min Act: -0.1700
Data Index: 983240 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7816. Min Range: -5.7816
Max Act: 5.5941. Min Act: -0.1700
Data Index: 8810226 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7816. Min Range: -5.7816
Max Act: 5.5941. Min Act: -0.1700
Data Index: 2250683 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7816. Min Range: -5.7816
Max Act: 5.5941. Min Act: -0.1700
Data Index: 8373557 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7816. Min Range: -5.7816
Max Act: 5.6253. Min Act: -0.1700
Data Index: 4432850 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7816. Min Range: -5.7816
Max Act: 5.5941. Min Act: -0.1700
Data Index: 7090150 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7816. Min Range: -5.7816
Max Act: 5.5941. Min Act: -0.1700
Data Index: 3729531 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7816. Min Range: -5.7816
Max Act: 5.5628. Min Act: -0.1700
Data Index: 1615108 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7816. Min Range: -5.7816
Max Act: 5.5941. Min Act: -0.1700
Data Index: 6627645 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7816. Min Range: -5.7816
Max Act: 5.5628. Min Act: -0.1700
Data Index: 4835791 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7816. Min Range: -5.7816
Max Act: 5.5628. Min Act: -0.1700
Data Index: 1430386 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7816. Min Range: -5.7816
Max Act: 5.5316. Min Act: -0.1700
Data Index: 4899347 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7816. Min Range: -5.7816
Max Act: 5.5316. Min Act: -0.1700
Data Index: 3633068 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7816. Min Range: -5.7816
Max Act: 5.5003. Min Act: -0.1700
Data Index: 6020453 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7816. Min Range: -5.7816
Max Act: 5.5003. Min Act: -0.1700
Data Index: 6303953 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7816. Min Range: -5.7816
Max Act: 5.5003. Min Act: -0.1700
Data Index: 652573 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19