Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1479 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2041. Min Range: -2.2041
Max Act: 2.2041. Min Act: -0.1700
Data Index: 3046841 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2041. Min Range: -2.2041
Max Act: 2.1709. Min Act: -0.1700
Data Index: 3173864 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2041. Min Range: -2.2041
Max Act: 2.1209. Min Act: -0.1700
Data Index: 3273999 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2041. Min Range: -2.2041
Max Act: 2.1543. Min Act: -0.1700
Data Index: 7469642 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2041. Min Range: -2.2041
Max Act: 2.1042. Min Act: -0.1700
Data Index: 8112846 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2041. Min Range: -2.2041
Max Act: 2.1042. Min Act: -0.1700
Data Index: 516322 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2041. Min Range: -2.2041
Max Act: 2.0874. Min Act: -0.1700
Data Index: 3983550 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2041. Min Range: -2.2041
Max Act: 2.1209. Min Act: -0.1700
Data Index: 1327782 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2041. Min Range: -2.2041
Max Act: 2.1042. Min Act: -0.1700
Data Index: 6267848 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2041. Min Range: -2.2041
Max Act: 2.0874. Min Act: -0.1700
Data Index: 4764371 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2041. Min Range: -2.2041
Max Act: 2.1042. Min Act: -0.1700
Data Index: 2005807 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2041. Min Range: -2.2041
Max Act: 2.1042. Min Act: -0.1700
Data Index: 4429087 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2041. Min Range: -2.2041
Max Act: 2.1042. Min Act: -0.1700
Data Index: 1057448 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2041. Min Range: -2.2041
Max Act: 2.1042. Min Act: -0.1700
Data Index: 4232490 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2041. Min Range: -2.2041
Max Act: 2.0706. Min Act: -0.1700
Data Index: 641718 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2041. Min Range: -2.2041
Max Act: 2.1042. Min Act: -0.1700
Data Index: 8212525 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2041. Min Range: -2.2041
Max Act: 2.0874. Min Act: -0.1700
Data Index: 7453285 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2041. Min Range: -2.2041
Max Act: 2.0874. Min Act: -0.1700
Data Index: 6802584 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2041. Min Range: -2.2041
Max Act: 2.0706. Min Act: -0.1700
Data Index: 6394714 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2041. Min Range: -2.2041
Max Act: 2.0874. Min Act: -0.1700
Data Index: 2716022 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19