Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3638 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6970. Min Range: -7.6970
Max Act: 7.6970. Min Act: -0.1700
Data Index: 997997 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6970. Min Range: -7.6970
Max Act: 7.5407. Min Act: -0.1700
Data Index: 5015366 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6970. Min Range: -7.6970
Max Act: 7.5095. Min Act: -0.1700
Data Index: 2735504 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6970. Min Range: -7.6970
Max Act: 7.4470. Min Act: -0.1700
Data Index: 4312532 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6970. Min Range: -7.6970
Max Act: 7.5095. Min Act: -0.1700
Data Index: 7801783 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6970. Min Range: -7.6970
Max Act: 7.4470. Min Act: -0.1700
Data Index: 6757177 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6970. Min Range: -7.6970
Max Act: 7.2595. Min Act: -0.1700
Data Index: 1390434 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6970. Min Range: -7.6970
Max Act: 7.2595. Min Act: -0.1700
Data Index: 5728617 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6970. Min Range: -7.6970
Max Act: 7.2595. Min Act: -0.1700
Data Index: 195087 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6970. Min Range: -7.6970
Max Act: 7.2282. Min Act: -0.1700
Data Index: 6003766 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6970. Min Range: -7.6970
Max Act: 7.2282. Min Act: -0.1700
Data Index: 3223366 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6970. Min Range: -7.6970
Max Act: 7.1970. Min Act: -0.1700
Data Index: 334625 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6970. Min Range: -7.6970
Max Act: 7.1970. Min Act: -0.1700
Data Index: 1638062 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6970. Min Range: -7.6970
Max Act: 7.1657. Min Act: -0.1700
Data Index: 2581459 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6970. Min Range: -7.6970
Max Act: 7.1032. Min Act: -0.1700
Data Index: 4084935 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6970. Min Range: -7.6970
Max Act: 7.1345. Min Act: -0.1700
Data Index: 4730999 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6970. Min Range: -7.6970
Max Act: 7.1032. Min Act: -0.1700
Data Index: 8141404 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6970. Min Range: -7.6970
Max Act: 7.1032. Min Act: -0.1700
Data Index: 5294338 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6970. Min Range: -7.6970
Max Act: 7.1032. Min Act: -0.1700
Data Index: 2584598 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6970. Min Range: -7.6970
Max Act: 7.0720. Min Act: -0.1700
Data Index: 7639108 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19