Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3364 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.8130. Min Act: -0.1700
Data Index: 1223795 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.7505. Min Act: -0.1700
Data Index: 3443669 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.6880. Min Act: -0.1700
Data Index: 425080 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.6255. Min Act: -0.1700
Data Index: 3628475 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.5943. Min Act: -0.1700
Data Index: 8469808 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.5005. Min Act: -0.1700
Data Index: 1665789 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.4693. Min Act: -0.1700
Data Index: 2996452 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.4693. Min Act: -0.1700
Data Index: 1679411 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.4380. Min Act: -0.1700
Data Index: 1081555 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.4380. Min Act: -0.1700
Data Index: 4045657 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.3755. Min Act: -0.1700
Data Index: 4571662 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.3755. Min Act: -0.1700
Data Index: 6203292 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.4068. Min Act: -0.1700
Data Index: 6883701 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.3443. Min Act: -0.1700
Data Index: 7237052 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.3443. Min Act: -0.1700
Data Index: 4352136 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.3443. Min Act: -0.1700
Data Index: 3067620 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.3443. Min Act: -0.1700
Data Index: 2057999 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.3443. Min Act: -0.1700
Data Index: 6964414 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.3130. Min Act: -0.1700
Data Index: 2372658 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.3130. Min Act: -0.1700
Data Index: 3977347 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19