Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3316 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2367. Min Range: -6.2367
Max Act: 6.2367. Min Act: -0.1700
Data Index: 4848243 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2367. Min Range: -6.2367
Max Act: 6.1430. Min Act: -0.1700
Data Index: 4101586 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2367. Min Range: -6.2367
Max Act: 6.1430. Min Act: -0.1700
Data Index: 4403089 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2367. Min Range: -6.2367
Max Act: 6.0180. Min Act: -0.1700
Data Index: 4261566 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2367. Min Range: -6.2367
Max Act: 6.0180. Min Act: -0.1700
Data Index: 20996 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2367. Min Range: -6.2367
Max Act: 5.9555. Min Act: -0.1700
Data Index: 5104365 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2367. Min Range: -6.2367
Max Act: 5.8930. Min Act: -0.1700
Data Index: 3813457 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2367. Min Range: -6.2367
Max Act: 5.8617. Min Act: -0.1700
Data Index: 6551048 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2367. Min Range: -6.2367
Max Act: 5.8617. Min Act: -0.1700
Data Index: 8421955 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2367. Min Range: -6.2367
Max Act: 5.8305. Min Act: -0.1700
Data Index: 5612578 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2367. Min Range: -6.2367
Max Act: 5.8305. Min Act: -0.1700
Data Index: 5340032 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2367. Min Range: -6.2367
Max Act: 5.7992. Min Act: -0.1700
Data Index: 3870303 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2367. Min Range: -6.2367
Max Act: 5.7992. Min Act: -0.1700
Data Index: 4467541 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2367. Min Range: -6.2367
Max Act: 5.7680. Min Act: -0.1700
Data Index: 6426178 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2367. Min Range: -6.2367
Max Act: 5.7680. Min Act: -0.1700
Data Index: 2808180 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2367. Min Range: -6.2367
Max Act: 5.7680. Min Act: -0.1700
Data Index: 6021453 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2367. Min Range: -6.2367
Max Act: 5.7055. Min Act: -0.1700
Data Index: 7332868 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2367. Min Range: -6.2367
Max Act: 5.7367. Min Act: -0.1700
Data Index: 2403418 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2367. Min Range: -6.2367
Max Act: 5.7367. Min Act: -0.1700
Data Index: 4677235 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2367. Min Range: -6.2367
Max Act: 5.7367. Min Act: -0.1700
Data Index: 5489779 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19