Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2533 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3851. Min Range: -7.3851
Max Act: 7.3851. Min Act: -0.1700
Data Index: 204228 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3851. Min Range: -7.3851
Max Act: 7.3851. Min Act: -0.1700
Data Index: 3581369 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3851. Min Range: -7.3851
Max Act: 7.2288. Min Act: -0.1700
Data Index: 2960181 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3851. Min Range: -7.3851
Max Act: 7.2288. Min Act: -0.1700
Data Index: 7470540 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3851. Min Range: -7.3851
Max Act: 7.2288. Min Act: -0.1700
Data Index: 3324789 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3851. Min Range: -7.3851
Max Act: 7.1976. Min Act: -0.1700
Data Index: 4280307 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3851. Min Range: -7.3851
Max Act: 7.1663. Min Act: -0.1700
Data Index: 2899743 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3851. Min Range: -7.3851
Max Act: 7.1351. Min Act: -0.1700
Data Index: 4942207 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3851. Min Range: -7.3851
Max Act: 7.1038. Min Act: -0.1700
Data Index: 2511495 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3851. Min Range: -7.3851
Max Act: 7.0101. Min Act: -0.1700
Data Index: 5768836 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3851. Min Range: -7.3851
Max Act: 7.0413. Min Act: -0.1700
Data Index: 5635847 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3851. Min Range: -7.3851
Max Act: 7.0101. Min Act: -0.1700
Data Index: 2067161 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3851. Min Range: -7.3851
Max Act: 7.0101. Min Act: -0.1700
Data Index: 3912959 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3851. Min Range: -7.3851
Max Act: 7.0101. Min Act: -0.1700
Data Index: 4844782 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3851. Min Range: -7.3851
Max Act: 6.9788. Min Act: -0.1700
Data Index: 5585198 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3851. Min Range: -7.3851
Max Act: 6.9788. Min Act: -0.1700
Data Index: 6008233 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3851. Min Range: -7.3851
Max Act: 6.9476. Min Act: -0.1700
Data Index: 3683836 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3851. Min Range: -7.3851
Max Act: 6.9476. Min Act: -0.1700
Data Index: 308923 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3851. Min Range: -7.3851
Max Act: 6.9163. Min Act: -0.1700
Data Index: 8826301 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3851. Min Range: -7.3851
Max Act: 6.8851. Min Act: -0.1700
Data Index: 177754 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19