Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4019 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6319. Min Range: -5.6319
Max Act: 5.6319. Min Act: -0.1700
Data Index: 5532844 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6319. Min Range: -5.6319
Max Act: 5.4756. Min Act: -0.1700
Data Index: 1403062 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6319. Min Range: -5.6319
Max Act: 5.4131. Min Act: -0.1700
Data Index: 848859 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6319. Min Range: -5.6319
Max Act: 5.4131. Min Act: -0.1700
Data Index: 5097404 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6319. Min Range: -5.6319
Max Act: 5.2881. Min Act: -0.1700
Data Index: 7319856 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6319. Min Range: -5.6319
Max Act: 5.3194. Min Act: -0.1700
Data Index: 6215333 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6319. Min Range: -5.6319
Max Act: 5.3194. Min Act: -0.1700
Data Index: 2273961 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6319. Min Range: -5.6319
Max Act: 5.2569. Min Act: -0.1700
Data Index: 4638466 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6319. Min Range: -5.6319
Max Act: 5.2256. Min Act: -0.1700
Data Index: 3277622 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6319. Min Range: -5.6319
Max Act: 5.2256. Min Act: -0.1700
Data Index: 6749349 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6319. Min Range: -5.6319
Max Act: 5.1944. Min Act: -0.1700
Data Index: 4325428 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6319. Min Range: -5.6319
Max Act: 5.1944. Min Act: -0.1700
Data Index: 3282179 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6319. Min Range: -5.6319
Max Act: 5.1944. Min Act: -0.1700
Data Index: 8418391 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6319. Min Range: -5.6319
Max Act: 5.1944. Min Act: -0.1700
Data Index: 588612 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6319. Min Range: -5.6319
Max Act: 5.1944. Min Act: -0.1700
Data Index: 6764861 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6319. Min Range: -5.6319
Max Act: 5.1631. Min Act: -0.1700
Data Index: 5673244 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6319. Min Range: -5.6319
Max Act: 5.1944. Min Act: -0.1700
Data Index: 7674680 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6319. Min Range: -5.6319
Max Act: 5.1944. Min Act: -0.1700
Data Index: 5464031 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6319. Min Range: -5.6319
Max Act: 5.1631. Min Act: -0.1700
Data Index: 1753693 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6319. Min Range: -5.6319
Max Act: 5.1944. Min Act: -0.1700
Data Index: 1034788 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19