Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4075 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0416. Min Range: -6.0416
Max Act: 6.0416. Min Act: -0.1700
Data Index: 6937368 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.6041. Min Act: -0.1700
Data Index: 2559964 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.4478. Min Act: -0.1700
Data Index: 4581136 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.4791. Min Act: -0.1700
Data Index: 8776304 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.4166. Min Act: -0.1700
Data Index: 6098169 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.3228. Min Act: -0.1700
Data Index: 4960212 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.2916. Min Act: -0.1700
Data Index: 5866156 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.2603. Min Act: -0.1700
Data Index: 4317645 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.2603. Min Act: -0.1700
Data Index: 5846196 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.2603. Min Act: -0.1700
Data Index: 8635740 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.2291. Min Act: -0.1700
Data Index: 8345330 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.2603. Min Act: -0.1700
Data Index: 6333717 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.2916. Min Act: -0.1700
Data Index: 7485060 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.2291. Min Act: -0.1700
Data Index: 820484 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.2291. Min Act: -0.1700
Data Index: 6401280 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.2603. Min Act: -0.1700
Data Index: 3082210 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.2291. Min Act: -0.1700
Data Index: 5205232 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.2291. Min Act: -0.1700
Data Index: 4732745 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.2291. Min Act: -0.1700
Data Index: 3675306 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0416. Min Range: -6.0416
Max Act: 5.2291. Min Act: -0.1700
Data Index: 4734144 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19