Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2121 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.0000. Min Range: -9.0000
Max Act: 8.8750. Min Act: -0.1700
Data Index: 8366834 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0000. Min Range: -9.0000
Max Act: 8.8125. Min Act: -0.1700
Data Index: 6668254 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0000. Min Range: -9.0000
Max Act: 8.8750. Min Act: -0.1700
Data Index: 3899305 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0000. Min Range: -9.0000
Max Act: 9.0000. Min Act: -0.1700
Data Index: 5656407 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0000. Min Range: -9.0000
Max Act: 8.8750. Min Act: -0.1700
Data Index: 2812884 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0000. Min Range: -9.0000
Max Act: 8.8125. Min Act: -0.1700
Data Index: 1675031 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0000. Min Range: -9.0000
Max Act: 8.8125. Min Act: -0.1700
Data Index: 556092 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0000. Min Range: -9.0000
Max Act: 8.8125. Min Act: -0.1700
Data Index: 4368118 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0000. Min Range: -9.0000
Max Act: 8.8125. Min Act: -0.1700
Data Index: 7858735 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0000. Min Range: -9.0000
Max Act: 8.7500. Min Act: -0.1700
Data Index: 3460598 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0000. Min Range: -9.0000
Max Act: 8.6875. Min Act: -0.1700
Data Index: 4884325 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0000. Min Range: -9.0000
Max Act: 8.7500. Min Act: -0.1700
Data Index: 5807453 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0000. Min Range: -9.0000
Max Act: 8.6250. Min Act: -0.1700
Data Index: 7992635 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0000. Min Range: -9.0000
Max Act: 8.7500. Min Act: -0.1700
Data Index: 219582 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0000. Min Range: -9.0000
Max Act: 8.6875. Min Act: -0.1700
Data Index: 3145456 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0000. Min Range: -9.0000
Max Act: 8.6875. Min Act: -0.1700
Data Index: 4055828 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0000. Min Range: -9.0000
Max Act: 8.6875. Min Act: -0.1700
Data Index: 2736948 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0000. Min Range: -9.0000
Max Act: 8.6250. Min Act: -0.1700
Data Index: 3349107 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0000. Min Range: -9.0000
Max Act: 8.6250. Min Act: -0.1700
Data Index: 2410320 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0000. Min Range: -9.0000
Max Act: 8.6250. Min Act: -0.1700
Data Index: 2387701 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19