Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 172 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0331. Min Range: -3.0331
Max Act: 3.0331. Min Act: -0.1700
Data Index: 8548723 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0331. Min Range: -3.0331
Max Act: 2.9857. Min Act: -0.1700
Data Index: 2559529 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0331. Min Range: -3.0331
Max Act: 3.0173. Min Act: -0.1700
Data Index: 7608785 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0331. Min Range: -3.0331
Max Act: 2.9699. Min Act: -0.1700
Data Index: 7608784 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0331. Min Range: -3.0331
Max Act: 2.9540. Min Act: -0.1700
Data Index: 3532392 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0331. Min Range: -3.0331
Max Act: 2.9382. Min Act: -0.1700
Data Index: 5559381 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0331. Min Range: -3.0331
Max Act: 2.9540. Min Act: -0.1700
Data Index: 8444252 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0331. Min Range: -3.0331
Max Act: 2.9382. Min Act: -0.1700
Data Index: 5003533 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0331. Min Range: -3.0331
Max Act: 2.9224. Min Act: -0.1700
Data Index: 414187 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0331. Min Range: -3.0331
Max Act: 2.9065. Min Act: -0.1700
Data Index: 2770338 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0331. Min Range: -3.0331
Max Act: 2.9065. Min Act: -0.1700
Data Index: 1160755 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0331. Min Range: -3.0331
Max Act: 2.8748. Min Act: -0.1700
Data Index: 2011485 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0331. Min Range: -3.0331
Max Act: 2.8907. Min Act: -0.1700
Data Index: 7483144 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0331. Min Range: -3.0331
Max Act: 2.8748. Min Act: -0.1700
Data Index: 7378530 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0331. Min Range: -3.0331
Max Act: 2.8748. Min Act: -0.1700
Data Index: 142004 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0331. Min Range: -3.0331
Max Act: 2.8589. Min Act: -0.1700
Data Index: 6551147 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0331. Min Range: -3.0331
Max Act: 2.8907. Min Act: -0.1700
Data Index: 4966859 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0331. Min Range: -3.0331
Max Act: 2.8589. Min Act: -0.1700
Data Index: 6607842 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0331. Min Range: -3.0331
Max Act: 2.8271. Min Act: -0.1700
Data Index: 8692080 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0331. Min Range: -3.0331
Max Act: 2.8589. Min Act: -0.1700
Data Index: 309756 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19