Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2729 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1557. Min Range: -9.1557
Max Act: 9.1557. Min Act: -0.1700
Data Index: 2109377 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1557. Min Range: -9.1557
Max Act: 9.1557. Min Act: -0.1700
Data Index: 4298847 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1557. Min Range: -9.1557
Max Act: 9.0307. Min Act: -0.1700
Data Index: 2109380 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1557. Min Range: -9.1557
Max Act: 8.8432. Min Act: -0.1700
Data Index: 4298834 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1557. Min Range: -9.1557
Max Act: 8.7807. Min Act: -0.1700
Data Index: 3488764 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1557. Min Range: -9.1557
Max Act: 8.7807. Min Act: -0.1700
Data Index: 2608751 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1557. Min Range: -9.1557
Max Act: 8.7182. Min Act: -0.1700
Data Index: 4395034 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1557. Min Range: -9.1557
Max Act: 8.7182. Min Act: -0.1700
Data Index: 4395035 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1557. Min Range: -9.1557
Max Act: 8.7182. Min Act: -0.1700
Data Index: 7123328 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1557. Min Range: -9.1557
Max Act: 8.7182. Min Act: -0.1700
Data Index: 2992133 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1557. Min Range: -9.1557
Max Act: 8.7182. Min Act: -0.1700
Data Index: 3742407 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1557. Min Range: -9.1557
Max Act: 8.7182. Min Act: -0.1700
Data Index: 1320056 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1557. Min Range: -9.1557
Max Act: 8.6557. Min Act: -0.1700
Data Index: 3048192 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1557. Min Range: -9.1557
Max Act: 8.6557. Min Act: -0.1700
Data Index: 5421695 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1557. Min Range: -9.1557
Max Act: 8.5932. Min Act: -0.1700
Data Index: 5961331 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1557. Min Range: -9.1557
Max Act: 8.6557. Min Act: -0.1700
Data Index: 3331391 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1557. Min Range: -9.1557
Max Act: 8.6557. Min Act: -0.1700
Data Index: 298667 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1557. Min Range: -9.1557
Max Act: 8.6557. Min Act: -0.1700
Data Index: 4298841 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1557. Min Range: -9.1557
Max Act: 8.6557. Min Act: -0.1700
Data Index: 6150467 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1557. Min Range: -9.1557
Max Act: 8.5932. Min Act: -0.1700
Data Index: 5720460 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19