Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3212 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6474. Min Range: -6.6474
Max Act: 6.6474. Min Act: -0.1700
Data Index: 694880 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6474. Min Range: -6.6474
Max Act: 6.3349. Min Act: -0.1700
Data Index: 294259 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6474. Min Range: -6.6474
Max Act: 6.3349. Min Act: -0.1700
Data Index: 503604 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6474. Min Range: -6.6474
Max Act: 6.2411. Min Act: -0.1700
Data Index: 767540 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6474. Min Range: -6.6474
Max Act: 6.2411. Min Act: -0.1700
Data Index: 6180889 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6474. Min Range: -6.6474
Max Act: 6.2411. Min Act: -0.1700
Data Index: 3756369 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6474. Min Range: -6.6474
Max Act: 6.2099. Min Act: -0.1700
Data Index: 5562125 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6474. Min Range: -6.6474
Max Act: 6.1786. Min Act: -0.1700
Data Index: 1714217 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6474. Min Range: -6.6474
Max Act: 6.1161. Min Act: -0.1700
Data Index: 6406907 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6474. Min Range: -6.6474
Max Act: 6.1161. Min Act: -0.1700
Data Index: 1867469 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6474. Min Range: -6.6474
Max Act: 6.1474. Min Act: -0.1700
Data Index: 8799602 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6474. Min Range: -6.6474
Max Act: 6.0849. Min Act: -0.1700
Data Index: 465518 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6474. Min Range: -6.6474
Max Act: 6.1161. Min Act: -0.1700
Data Index: 4666175 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6474. Min Range: -6.6474
Max Act: 6.0536. Min Act: -0.1700
Data Index: 1157483 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6474. Min Range: -6.6474
Max Act: 6.0536. Min Act: -0.1700
Data Index: 3092796 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6474. Min Range: -6.6474
Max Act: 6.0224. Min Act: -0.1700
Data Index: 5038365 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6474. Min Range: -6.6474
Max Act: 6.0536. Min Act: -0.1700
Data Index: 6058479 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6474. Min Range: -6.6474
Max Act: 6.0536. Min Act: -0.1700
Data Index: 4606636 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6474. Min Range: -6.6474
Max Act: 6.0224. Min Act: -0.1700
Data Index: 4725723 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6474. Min Range: -6.6474
Max Act: 6.0224. Min Act: -0.1700
Data Index: 2039008 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19