Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 577 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0864. Min Act: -0.1700
Data Index: 8761136 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0548. Min Act: -0.1700
Data Index: 1847066 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0548. Min Act: -0.1700
Data Index: 4618391 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0548. Min Act: -0.1700
Data Index: 1251568 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0390. Min Act: -0.1700
Data Index: 620510 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0706. Min Act: -0.1700
Data Index: 3691777 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0390. Min Act: -0.1700
Data Index: 2888525 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0390. Min Act: -0.1700
Data Index: 3398833 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0390. Min Act: -0.1700
Data Index: 2418177 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0390. Min Act: -0.1700
Data Index: 2101284 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0232. Min Act: -0.1700
Data Index: 5681698 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0232. Min Act: -0.1700
Data Index: 6074702 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0232. Min Act: -0.1700
Data Index: 6207099 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0074. Min Act: -0.1700
Data Index: 3315504 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0074. Min Act: -0.1700
Data Index: 2755855 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0074. Min Act: -0.1700
Data Index: 6888744 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0232. Min Act: -0.1700
Data Index: 6976855 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0232. Min Act: -0.1700
Data Index: 1610530 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0232. Min Act: -0.1700
Data Index: 6987609 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0074. Min Act: -0.1700
Data Index: 117482 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19