Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3642 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6465. Min Range: -5.6465
Max Act: 5.6465. Min Act: -0.1700
Data Index: 7560577 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6465. Min Range: -5.6465
Max Act: 5.5840. Min Act: -0.1700
Data Index: 1761148 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6465. Min Range: -5.6465
Max Act: 5.5215. Min Act: -0.1700
Data Index: 6264416 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6465. Min Range: -5.6465
Max Act: 5.5215. Min Act: -0.1700
Data Index: 5554506 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6465. Min Range: -5.6465
Max Act: 5.4902. Min Act: -0.1700
Data Index: 2948994 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6465. Min Range: -5.6465
Max Act: 5.4590. Min Act: -0.1700
Data Index: 8227904 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6465. Min Range: -5.6465
Max Act: 5.3965. Min Act: -0.1700
Data Index: 3418643 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6465. Min Range: -5.6465
Max Act: 5.3340. Min Act: -0.1700
Data Index: 5686311 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6465. Min Range: -5.6465
Max Act: 5.3340. Min Act: -0.1700
Data Index: 2389445 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6465. Min Range: -5.6465
Max Act: 5.3027. Min Act: -0.1700
Data Index: 345215 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6465. Min Range: -5.6465
Max Act: 5.2715. Min Act: -0.1700
Data Index: 6972110 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6465. Min Range: -5.6465
Max Act: 5.2715. Min Act: -0.1700
Data Index: 6630622 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6465. Min Range: -5.6465
Max Act: 5.2402. Min Act: -0.1700
Data Index: 3473809 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6465. Min Range: -5.6465
Max Act: 5.2402. Min Act: -0.1700
Data Index: 7264164 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6465. Min Range: -5.6465
Max Act: 5.2402. Min Act: -0.1700
Data Index: 4965406 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6465. Min Range: -5.6465
Max Act: 5.2090. Min Act: -0.1700
Data Index: 3364808 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6465. Min Range: -5.6465
Max Act: 5.1777. Min Act: -0.1700
Data Index: 1730101 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6465. Min Range: -5.6465
Max Act: 5.2090. Min Act: -0.1700
Data Index: 5511463 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6465. Min Range: -5.6465
Max Act: 5.2090. Min Act: -0.1700
Data Index: 4800968 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6465. Min Range: -5.6465
Max Act: 5.1777. Min Act: -0.1700
Data Index: 3490544 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19