Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5940 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7279. Min Range: -6.7279
Max Act: 6.7279. Min Act: -0.1700
Data Index: 5458357 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7279. Min Range: -6.7279
Max Act: 6.3841. Min Act: -0.1700
Data Index: 5458355 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7279. Min Range: -6.7279
Max Act: 6.2904. Min Act: -0.1700
Data Index: 557314 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7279. Min Range: -6.7279
Max Act: 6.2904. Min Act: -0.1700
Data Index: 8393213 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7279. Min Range: -6.7279
Max Act: 6.2591. Min Act: -0.1700
Data Index: 1757731 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7279. Min Range: -6.7279
Max Act: 6.2279. Min Act: -0.1700
Data Index: 1705292 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7279. Min Range: -6.7279
Max Act: 6.1966. Min Act: -0.1700
Data Index: 7338220 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7279. Min Range: -6.7279
Max Act: 6.1654. Min Act: -0.1700
Data Index: 4164555 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7279. Min Range: -6.7279
Max Act: 6.1654. Min Act: -0.1700
Data Index: 7926344 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7279. Min Range: -6.7279
Max Act: 6.1341. Min Act: -0.1700
Data Index: 4947517 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7279. Min Range: -6.7279
Max Act: 6.1654. Min Act: -0.1700
Data Index: 3831185 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7279. Min Range: -6.7279
Max Act: 6.1029. Min Act: -0.1700
Data Index: 2411843 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7279. Min Range: -6.7279
Max Act: 6.0716. Min Act: -0.1700
Data Index: 1899315 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7279. Min Range: -6.7279
Max Act: 6.0716. Min Act: -0.1700
Data Index: 8826058 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7279. Min Range: -6.7279
Max Act: 6.0716. Min Act: -0.1700
Data Index: 418066 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7279. Min Range: -6.7279
Max Act: 6.0404. Min Act: -0.1700
Data Index: 1490756 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7279. Min Range: -6.7279
Max Act: 6.0716. Min Act: -0.1700
Data Index: 7039595 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7279. Min Range: -6.7279
Max Act: 6.0716. Min Act: -0.1700
Data Index: 4893400 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7279. Min Range: -6.7279
Max Act: 6.0404. Min Act: -0.1700
Data Index: 6191216 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7279. Min Range: -6.7279
Max Act: 6.0716. Min Act: -0.1700
Data Index: 3850867 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19