Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4912 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4534. Min Range: -9.4534
Max Act: 9.4534. Min Act: -0.1700
Data Index: 1956855 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4534. Min Range: -9.4534
Max Act: 9.2659. Min Act: -0.1700
Data Index: 3323415 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4534. Min Range: -9.4534
Max Act: 9.0784. Min Act: -0.1700
Data Index: 8795249 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4534. Min Range: -9.4534
Max Act: 8.8909. Min Act: -0.1700
Data Index: 303387 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4534. Min Range: -9.4534
Max Act: 8.8284. Min Act: -0.1700
Data Index: 7419971 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4534. Min Range: -9.4534
Max Act: 8.8284. Min Act: -0.1700
Data Index: 1633642 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4534. Min Range: -9.4534
Max Act: 8.8284. Min Act: -0.1700
Data Index: 4990039 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4534. Min Range: -9.4534
Max Act: 8.7659. Min Act: -0.1700
Data Index: 4035778 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4534. Min Range: -9.4534
Max Act: 8.7034. Min Act: -0.1700
Data Index: 2912722 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4534. Min Range: -9.4534
Max Act: 8.6409. Min Act: -0.1700
Data Index: 4672834 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4534. Min Range: -9.4534
Max Act: 8.7034. Min Act: -0.1700
Data Index: 8007378 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4534. Min Range: -9.4534
Max Act: 8.7034. Min Act: -0.1700
Data Index: 2593600 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4534. Min Range: -9.4534
Max Act: 8.7034. Min Act: -0.1700
Data Index: 7652879 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4534. Min Range: -9.4534
Max Act: 8.7034. Min Act: -0.1700
Data Index: 2834063 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4534. Min Range: -9.4534
Max Act: 8.6409. Min Act: -0.1700
Data Index: 1575882 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4534. Min Range: -9.4534
Max Act: 8.6409. Min Act: -0.1700
Data Index: 6309644 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4534. Min Range: -9.4534
Max Act: 8.6409. Min Act: -0.1700
Data Index: 6607586 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4534. Min Range: -9.4534
Max Act: 8.5784. Min Act: -0.1700
Data Index: 988940 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4534. Min Range: -9.4534
Max Act: 8.5784. Min Act: -0.1700
Data Index: 3007689 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4534. Min Range: -9.4534
Max Act: 8.5784. Min Act: -0.1700
Data Index: 3316262 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19