Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4777 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0033. Min Range: -8.0033
Max Act: 8.0033. Min Act: -0.1700
Data Index: 4778096 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0033. Min Range: -8.0033
Max Act: 7.9408. Min Act: -0.1700
Data Index: 84581 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0033. Min Range: -8.0033
Max Act: 7.7533. Min Act: -0.1700
Data Index: 7884612 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0033. Min Range: -8.0033
Max Act: 7.6908. Min Act: -0.1700
Data Index: 1165963 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0033. Min Range: -8.0033
Max Act: 7.5346. Min Act: -0.1700
Data Index: 5682513 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0033. Min Range: -8.0033
Max Act: 7.5346. Min Act: -0.1700
Data Index: 2134865 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0033. Min Range: -8.0033
Max Act: 7.4721. Min Act: -0.1700
Data Index: 5087047 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0033. Min Range: -8.0033
Max Act: 7.4721. Min Act: -0.1700
Data Index: 1845539 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0033. Min Range: -8.0033
Max Act: 7.4408. Min Act: -0.1700
Data Index: 7858877 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0033. Min Range: -8.0033
Max Act: 7.4408. Min Act: -0.1700
Data Index: 4229629 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0033. Min Range: -8.0033
Max Act: 7.4408. Min Act: -0.1700
Data Index: 8498254 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0033. Min Range: -8.0033
Max Act: 7.3471. Min Act: -0.1700
Data Index: 1179121 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0033. Min Range: -8.0033
Max Act: 7.2846. Min Act: -0.1700
Data Index: 3379306 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0033. Min Range: -8.0033
Max Act: 7.2846. Min Act: -0.1700
Data Index: 6781349 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0033. Min Range: -8.0033
Max Act: 7.2533. Min Act: -0.1700
Data Index: 5039649 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0033. Min Range: -8.0033
Max Act: 7.2533. Min Act: -0.1700
Data Index: 8647402 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0033. Min Range: -8.0033
Max Act: 7.2846. Min Act: -0.1700
Data Index: 196569 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0033. Min Range: -8.0033
Max Act: 7.2221. Min Act: -0.1700
Data Index: 4935212 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0033. Min Range: -8.0033
Max Act: 7.2221. Min Act: -0.1700
Data Index: 2665657 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0033. Min Range: -8.0033
Max Act: 7.2221. Min Act: -0.1700
Data Index: 5600897 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19