Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4474 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4474. Min Range: -2.4474
Max Act: 2.4474. Min Act: -0.1700
Data Index: 2711474 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4474. Min Range: -2.4474
Max Act: 2.4474. Min Act: -0.1700
Data Index: 4961352 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4474. Min Range: -2.4474
Max Act: 2.4149. Min Act: -0.1700
Data Index: 948024 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4474. Min Range: -2.4474
Max Act: 2.3986. Min Act: -0.1700
Data Index: 2545586 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4474. Min Range: -2.4474
Max Act: 2.3822. Min Act: -0.1700
Data Index: 262718 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4474. Min Range: -2.4474
Max Act: 2.3822. Min Act: -0.1700
Data Index: 5939922 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4474. Min Range: -2.4474
Max Act: 2.3659. Min Act: -0.1700
Data Index: 1378198 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4474. Min Range: -2.4474
Max Act: 2.3822. Min Act: -0.1700
Data Index: 5133585 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4474. Min Range: -2.4474
Max Act: 2.3659. Min Act: -0.1700
Data Index: 4727296 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4474. Min Range: -2.4474
Max Act: 2.3659. Min Act: -0.1700
Data Index: 7025761 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4474. Min Range: -2.4474
Max Act: 2.3495. Min Act: -0.1700
Data Index: 4136540 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4474. Min Range: -2.4474
Max Act: 2.3659. Min Act: -0.1700
Data Index: 900365 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4474. Min Range: -2.4474
Max Act: 2.3659. Min Act: -0.1700
Data Index: 3479678 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4474. Min Range: -2.4474
Max Act: 2.3167. Min Act: -0.1700
Data Index: 8351804 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4474. Min Range: -2.4474
Max Act: 2.3495. Min Act: -0.1700
Data Index: 8333715 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4474. Min Range: -2.4474
Max Act: 2.3331. Min Act: -0.1700
Data Index: 3176460 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4474. Min Range: -2.4474
Max Act: 2.3331. Min Act: -0.1700
Data Index: 455561 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4474. Min Range: -2.4474
Max Act: 2.3331. Min Act: -0.1700
Data Index: 3777956 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4474. Min Range: -2.4474
Max Act: 2.3167. Min Act: -0.1700
Data Index: 6410579 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4474. Min Range: -2.4474
Max Act: 2.3167. Min Act: -0.1700
Data Index: 4920692 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19