Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4581 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0612. Min Range: -6.0612
Max Act: 6.0612. Min Act: -0.1700
Data Index: 3886532 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0612. Min Range: -6.0612
Max Act: 5.9987. Min Act: -0.1700
Data Index: 7795363 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0612. Min Range: -6.0612
Max Act: 5.9362. Min Act: -0.1700
Data Index: 4321391 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0612. Min Range: -6.0612
Max Act: 5.9362. Min Act: -0.1700
Data Index: 7867899 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0612. Min Range: -6.0612
Max Act: 5.8737. Min Act: -0.1700
Data Index: 7094174 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0612. Min Range: -6.0612
Max Act: 5.8737. Min Act: -0.1700
Data Index: 1745809 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0612. Min Range: -6.0612
Max Act: 5.8737. Min Act: -0.1700
Data Index: 749933 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0612. Min Range: -6.0612
Max Act: 5.8112. Min Act: -0.1700
Data Index: 8477329 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0612. Min Range: -6.0612
Max Act: 5.8112. Min Act: -0.1700
Data Index: 3012688 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0612. Min Range: -6.0612
Max Act: 5.8112. Min Act: -0.1700
Data Index: 5254402 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0612. Min Range: -6.0612
Max Act: 5.7174. Min Act: -0.1700
Data Index: 8447171 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0612. Min Range: -6.0612
Max Act: 5.7174. Min Act: -0.1700
Data Index: 8778763 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0612. Min Range: -6.0612
Max Act: 5.7174. Min Act: -0.1700
Data Index: 3371855 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0612. Min Range: -6.0612
Max Act: 5.7174. Min Act: -0.1700
Data Index: 6704477 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0612. Min Range: -6.0612
Max Act: 5.6862. Min Act: -0.1700
Data Index: 2678051 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0612. Min Range: -6.0612
Max Act: 5.6862. Min Act: -0.1700
Data Index: 290750 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0612. Min Range: -6.0612
Max Act: 5.6862. Min Act: -0.1700
Data Index: 6121813 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0612. Min Range: -6.0612
Max Act: 5.6549. Min Act: -0.1700
Data Index: 2152757 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0612. Min Range: -6.0612
Max Act: 5.6862. Min Act: -0.1700
Data Index: 1360613 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0612. Min Range: -6.0612
Max Act: 5.6549. Min Act: -0.1700
Data Index: 4074415 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19