Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3474 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2971. Min Range: -7.2971
Max Act: 7.2971. Min Act: -0.1700
Data Index: 5066263 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2971. Min Range: -7.2971
Max Act: 7.2033. Min Act: -0.1700
Data Index: 7942664 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2971. Min Range: -7.2971
Max Act: 7.0158. Min Act: -0.1700
Data Index: 2131826 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2971. Min Range: -7.2971
Max Act: 7.0158. Min Act: -0.1700
Data Index: 2270143 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2971. Min Range: -7.2971
Max Act: 6.9533. Min Act: -0.1700
Data Index: 8450832 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2971. Min Range: -7.2971
Max Act: 6.9533. Min Act: -0.1700
Data Index: 3611799 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2971. Min Range: -7.2971
Max Act: 6.8908. Min Act: -0.1700
Data Index: 5827602 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2971. Min Range: -7.2971
Max Act: 6.8908. Min Act: -0.1700
Data Index: 2946450 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2971. Min Range: -7.2971
Max Act: 6.8283. Min Act: -0.1700
Data Index: 4904175 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2971. Min Range: -7.2971
Max Act: 6.8283. Min Act: -0.1700
Data Index: 8169934 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2971. Min Range: -7.2971
Max Act: 6.7971. Min Act: -0.1700
Data Index: 1525750 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2971. Min Range: -7.2971
Max Act: 6.7033. Min Act: -0.1700
Data Index: 7009457 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2971. Min Range: -7.2971
Max Act: 6.7033. Min Act: -0.1700
Data Index: 8599547 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2971. Min Range: -7.2971
Max Act: 6.7033. Min Act: -0.1700
Data Index: 1121669 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2971. Min Range: -7.2971
Max Act: 6.6721. Min Act: -0.1700
Data Index: 219085 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2971. Min Range: -7.2971
Max Act: 6.6721. Min Act: -0.1700
Data Index: 4560517 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2971. Min Range: -7.2971
Max Act: 6.6408. Min Act: -0.1700
Data Index: 7724174 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2971. Min Range: -7.2971
Max Act: 6.6408. Min Act: -0.1700
Data Index: 1538979 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2971. Min Range: -7.2971
Max Act: 6.6096. Min Act: -0.1700
Data Index: 101135 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2971. Min Range: -7.2971
Max Act: 6.6408. Min Act: -0.1700
Data Index: 487227 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19