Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 6 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.4545. Min Act: -0.1700
Data Index: 1765455 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.3134. Min Act: -0.1700
Data Index: 5386925 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.2977. Min Act: -0.1700
Data Index: 1852287 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.3291. Min Act: -0.1700
Data Index: 6672333 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.3291. Min Act: -0.1700
Data Index: 2462415 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.2977. Min Act: -0.1700
Data Index: 6171025 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.3134. Min Act: -0.1700
Data Index: 1666294 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.2663. Min Act: -0.1700
Data Index: 719229 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.2820. Min Act: -0.1700
Data Index: 6001578 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.2506. Min Act: -0.1700
Data Index: 5698389 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.2506. Min Act: -0.1700
Data Index: 1922099 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.2348. Min Act: -0.1700
Data Index: 5810408 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.2506. Min Act: -0.1700
Data Index: 7305094 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.2034. Min Act: -0.1700
Data Index: 2461138 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.2348. Min Act: -0.1700
Data Index: 1835106 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.2191. Min Act: -0.1700
Data Index: 192123 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.2034. Min Act: -0.1700
Data Index: 2133335 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.1562. Min Act: -0.1700
Data Index: 6522654 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.1562. Min Act: -0.1700
Data Index: 1679290 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4545. Min Range: -3.4545
Max Act: 3.1405. Min Act: -0.1700
Data Index: 2683668 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19