Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3062 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4341. Min Range: -4.4341
Max Act: 4.4341. Min Act: -0.1700
Data Index: 6991230 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4341. Min Range: -4.4341
Max Act: 4.1529. Min Act: -0.1700
Data Index: 7532240 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4341. Min Range: -4.4341
Max Act: 4.1529. Min Act: -0.1700
Data Index: 2756129 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4341. Min Range: -4.4341
Max Act: 4.1841. Min Act: -0.1700
Data Index: 920723 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4341. Min Range: -4.4341
Max Act: 4.1529. Min Act: -0.1700
Data Index: 1050788 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4341. Min Range: -4.4341
Max Act: 4.1216. Min Act: -0.1700
Data Index: 1106207 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4341. Min Range: -4.4341
Max Act: 4.0903. Min Act: -0.1700
Data Index: 8235441 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4341. Min Range: -4.4341
Max Act: 4.1216. Min Act: -0.1700
Data Index: 8585542 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4341. Min Range: -4.4341
Max Act: 4.0903. Min Act: -0.1700
Data Index: 5349076 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4341. Min Range: -4.4341
Max Act: 4.0903. Min Act: -0.1700
Data Index: 4044094 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4341. Min Range: -4.4341
Max Act: 4.0591. Min Act: -0.1700
Data Index: 1121335 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4341. Min Range: -4.4341
Max Act: 4.0591. Min Act: -0.1700
Data Index: 7917898 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4341. Min Range: -4.4341
Max Act: 4.0591. Min Act: -0.1700
Data Index: 8296700 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4341. Min Range: -4.4341
Max Act: 4.0278. Min Act: -0.1700
Data Index: 180922 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4341. Min Range: -4.4341
Max Act: 3.9966. Min Act: -0.1700
Data Index: 2721006 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4341. Min Range: -4.4341
Max Act: 3.9653. Min Act: -0.1700
Data Index: 4109385 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4341. Min Range: -4.4341
Max Act: 3.9653. Min Act: -0.1700
Data Index: 6274555 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4341. Min Range: -4.4341
Max Act: 3.9653. Min Act: -0.1700
Data Index: 79250 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4341. Min Range: -4.4341
Max Act: 3.9653. Min Act: -0.1700
Data Index: 3198 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4341. Min Range: -4.4341
Max Act: 3.9653. Min Act: -0.1700
Data Index: 4235639 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19