Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1388 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5288. Min Range: -5.5288
Max Act: 5.5288. Min Act: -0.1700
Data Index: 541551 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5288. Min Range: -5.5288
Max Act: 5.4663. Min Act: -0.1700
Data Index: 4244701 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5288. Min Range: -5.5288
Max Act: 5.3726. Min Act: -0.1700
Data Index: 143332 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5288. Min Range: -5.5288
Max Act: 5.2476. Min Act: -0.1700
Data Index: 6767068 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5288. Min Range: -5.5288
Max Act: 5.2788. Min Act: -0.1700
Data Index: 8720723 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5288. Min Range: -5.5288
Max Act: 5.2788. Min Act: -0.1700
Data Index: 584647 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5288. Min Range: -5.5288
Max Act: 5.2163. Min Act: -0.1700
Data Index: 4686616 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5288. Min Range: -5.5288
Max Act: 5.1851. Min Act: -0.1700
Data Index: 3163052 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5288. Min Range: -5.5288
Max Act: 5.1851. Min Act: -0.1700
Data Index: 4124761 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5288. Min Range: -5.5288
Max Act: 5.1538. Min Act: -0.1700
Data Index: 4253551 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5288. Min Range: -5.5288
Max Act: 5.1226. Min Act: -0.1700
Data Index: 4513479 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5288. Min Range: -5.5288
Max Act: 5.0913. Min Act: -0.1700
Data Index: 6100467 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5288. Min Range: -5.5288
Max Act: 5.0913. Min Act: -0.1700
Data Index: 509439 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5288. Min Range: -5.5288
Max Act: 5.0913. Min Act: -0.1700
Data Index: 5063759 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5288. Min Range: -5.5288
Max Act: 5.0601. Min Act: -0.1700
Data Index: 8549800 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5288. Min Range: -5.5288
Max Act: 5.0601. Min Act: -0.1700
Data Index: 6841623 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5288. Min Range: -5.5288
Max Act: 5.0601. Min Act: -0.1700
Data Index: 584661 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5288. Min Range: -5.5288
Max Act: 5.0288. Min Act: -0.1700
Data Index: 4051412 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5288. Min Range: -5.5288
Max Act: 5.0288. Min Act: -0.1700
Data Index: 143333 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5288. Min Range: -5.5288
Max Act: 5.0288. Min Act: -0.1700
Data Index: 6303851 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19