Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4090 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9757. Min Range: -5.9757
Max Act: 5.9757. Min Act: -0.1700
Data Index: 42263 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9757. Min Range: -5.9757
Max Act: 5.7569. Min Act: -0.1700
Data Index: 6150465 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9757. Min Range: -5.9757
Max Act: 5.6632. Min Act: -0.1700
Data Index: 6150475 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9757. Min Range: -5.9757
Max Act: 5.7257. Min Act: -0.1700
Data Index: 1235003 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9757. Min Range: -5.9757
Max Act: 5.6944. Min Act: -0.1700
Data Index: 2109382 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9757. Min Range: -5.9757
Max Act: 5.6319. Min Act: -0.1700
Data Index: 2129229 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9757. Min Range: -5.9757
Max Act: 5.6319. Min Act: -0.1700
Data Index: 375506 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9757. Min Range: -5.9757
Max Act: 5.5069. Min Act: -0.1700
Data Index: 3168741 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9757. Min Range: -5.9757
Max Act: 5.5069. Min Act: -0.1700
Data Index: 2196538 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9757. Min Range: -5.9757
Max Act: 5.6007. Min Act: -0.1700
Data Index: 2109379 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9757. Min Range: -5.9757
Max Act: 5.4444. Min Act: -0.1700
Data Index: 2064282 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9757. Min Range: -5.9757
Max Act: 5.4444. Min Act: -0.1700
Data Index: 4848607 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9757. Min Range: -5.9757
Max Act: 5.4444. Min Act: -0.1700
Data Index: 5252677 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9757. Min Range: -5.9757
Max Act: 5.4132. Min Act: -0.1700
Data Index: 6124645 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9757. Min Range: -5.9757
Max Act: 5.4132. Min Act: -0.1700
Data Index: 2304131 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9757. Min Range: -5.9757
Max Act: 5.3507. Min Act: -0.1700
Data Index: 3355802 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9757. Min Range: -5.9757
Max Act: 5.3194. Min Act: -0.1700
Data Index: 2215194 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9757. Min Range: -5.9757
Max Act: 5.3194. Min Act: -0.1700
Data Index: 3158809 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9757. Min Range: -5.9757
Max Act: 5.3194. Min Act: -0.1700
Data Index: 3158820 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9757. Min Range: -5.9757
Max Act: 5.3194. Min Act: -0.1700
Data Index: 1020482 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19