Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4479 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9965. Min Range: -6.9965
Max Act: 6.9965. Min Act: -0.1700
Data Index: 2749193 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9965. Min Range: -6.9965
Max Act: 6.9340. Min Act: -0.1700
Data Index: 8228618 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9965. Min Range: -6.9965
Max Act: 6.9340. Min Act: -0.1700
Data Index: 2094657 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9965. Min Range: -6.9965
Max Act: 6.8715. Min Act: -0.1700
Data Index: 4151050 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9965. Min Range: -6.9965
Max Act: 6.8715. Min Act: -0.1700
Data Index: 1951470 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9965. Min Range: -6.9965
Max Act: 6.9340. Min Act: -0.1700
Data Index: 5010553 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9965. Min Range: -6.9965
Max Act: 6.8402. Min Act: -0.1700
Data Index: 812798 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9965. Min Range: -6.9965
Max Act: 6.8402. Min Act: -0.1700
Data Index: 462668 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9965. Min Range: -6.9965
Max Act: 6.8402. Min Act: -0.1700
Data Index: 8672018 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9965. Min Range: -6.9965
Max Act: 6.8402. Min Act: -0.1700
Data Index: 8490145 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9965. Min Range: -6.9965
Max Act: 6.8090. Min Act: -0.1700
Data Index: 6548186 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9965. Min Range: -6.9965
Max Act: 6.8090. Min Act: -0.1700
Data Index: 157367 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9965. Min Range: -6.9965
Max Act: 6.8090. Min Act: -0.1700
Data Index: 242411 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9965. Min Range: -6.9965
Max Act: 6.7777. Min Act: -0.1700
Data Index: 7526610 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9965. Min Range: -6.9965
Max Act: 6.7465. Min Act: -0.1700
Data Index: 4716527 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9965. Min Range: -6.9965
Max Act: 6.7465. Min Act: -0.1700
Data Index: 977708 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9965. Min Range: -6.9965
Max Act: 6.7465. Min Act: -0.1700
Data Index: 8310947 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9965. Min Range: -6.9965
Max Act: 6.7152. Min Act: -0.1700
Data Index: 4253173 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9965. Min Range: -6.9965
Max Act: 6.6840. Min Act: -0.1700
Data Index: 5492580 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9965. Min Range: -6.9965
Max Act: 6.6840. Min Act: -0.1700
Data Index: 4032735 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19