Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4061 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6163. Min Range: -3.6163
Max Act: 3.6163. Min Act: -0.1700
Data Index: 8712179 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6163. Min Range: -3.6163
Max Act: 3.5536. Min Act: -0.1700
Data Index: 4034471 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6163. Min Range: -3.6163
Max Act: 3.5067. Min Act: -0.1700
Data Index: 3174238 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6163. Min Range: -3.6163
Max Act: 3.5223. Min Act: -0.1700
Data Index: 2051415 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6163. Min Range: -3.6163
Max Act: 3.5067. Min Act: -0.1700
Data Index: 1092219 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6163. Min Range: -3.6163
Max Act: 3.4597. Min Act: -0.1700
Data Index: 2985845 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6163. Min Range: -3.6163
Max Act: 3.4753. Min Act: -0.1700
Data Index: 3195269 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6163. Min Range: -3.6163
Max Act: 3.5067. Min Act: -0.1700
Data Index: 3410318 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6163. Min Range: -3.6163
Max Act: 3.4753. Min Act: -0.1700
Data Index: 5398256 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6163. Min Range: -3.6163
Max Act: 3.4910. Min Act: -0.1700
Data Index: 63525 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6163. Min Range: -3.6163
Max Act: 3.4283. Min Act: -0.1700
Data Index: 392092 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6163. Min Range: -3.6163
Max Act: 3.4283. Min Act: -0.1700
Data Index: 557592 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6163. Min Range: -3.6163
Max Act: 3.4127. Min Act: -0.1700
Data Index: 5321446 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6163. Min Range: -3.6163
Max Act: 3.4127. Min Act: -0.1700
Data Index: 7341658 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6163. Min Range: -3.6163
Max Act: 3.3656. Min Act: -0.1700
Data Index: 5121358 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6163. Min Range: -3.6163
Max Act: 3.4127. Min Act: -0.1700
Data Index: 3707126 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6163. Min Range: -3.6163
Max Act: 3.3970. Min Act: -0.1700
Data Index: 1217886 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6163. Min Range: -3.6163
Max Act: 3.3813. Min Act: -0.1700
Data Index: 2044559 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6163. Min Range: -3.6163
Max Act: 3.3970. Min Act: -0.1700
Data Index: 1059100 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6163. Min Range: -3.6163
Max Act: 3.3813. Min Act: -0.1700
Data Index: 3114559 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19