Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3301 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0163. Min Range: -8.0163
Max Act: 8.0163. Min Act: -0.1700
Data Index: 4566307 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0163. Min Range: -8.0163
Max Act: 8.0163. Min Act: -0.1700
Data Index: 8350862 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0163. Min Range: -8.0163
Max Act: 7.9538. Min Act: -0.1700
Data Index: 6062720 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0163. Min Range: -8.0163
Max Act: 7.9538. Min Act: -0.1700
Data Index: 7585382 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0163. Min Range: -8.0163
Max Act: 7.9538. Min Act: -0.1700
Data Index: 2190903 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0163. Min Range: -8.0163
Max Act: 7.8913. Min Act: -0.1700
Data Index: 5632871 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0163. Min Range: -8.0163
Max Act: 7.8288. Min Act: -0.1700
Data Index: 5216615 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0163. Min Range: -8.0163
Max Act: 7.8288. Min Act: -0.1700
Data Index: 2135435 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0163. Min Range: -8.0163
Max Act: 7.7976. Min Act: -0.1700
Data Index: 4393555 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0163. Min Range: -8.0163
Max Act: 7.8288. Min Act: -0.1700
Data Index: 628904 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0163. Min Range: -8.0163
Max Act: 7.7976. Min Act: -0.1700
Data Index: 5718391 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0163. Min Range: -8.0163
Max Act: 7.7663. Min Act: -0.1700
Data Index: 3094090 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0163. Min Range: -8.0163
Max Act: 7.7038. Min Act: -0.1700
Data Index: 2520529 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0163. Min Range: -8.0163
Max Act: 7.7351. Min Act: -0.1700
Data Index: 1800178 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0163. Min Range: -8.0163
Max Act: 7.7351. Min Act: -0.1700
Data Index: 1111364 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0163. Min Range: -8.0163
Max Act: 7.7038. Min Act: -0.1700
Data Index: 4463167 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0163. Min Range: -8.0163
Max Act: 7.7038. Min Act: -0.1700
Data Index: 8203122 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0163. Min Range: -8.0163
Max Act: 7.7038. Min Act: -0.1700
Data Index: 8138486 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0163. Min Range: -8.0163
Max Act: 7.7038. Min Act: -0.1700
Data Index: 5902850 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0163. Min Range: -8.0163
Max Act: 7.6726. Min Act: -0.1700
Data Index: 6607276 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19