Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3864 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1350. Min Range: -7.1350
Max Act: 7.1350. Min Act: -0.1700
Data Index: 1644362 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1350. Min Range: -7.1350
Max Act: 7.0413. Min Act: -0.1700
Data Index: 2449939 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1350. Min Range: -7.1350
Max Act: 6.8225. Min Act: -0.1700
Data Index: 2652545 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1350. Min Range: -7.1350
Max Act: 6.7913. Min Act: -0.1700
Data Index: 566869 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1350. Min Range: -7.1350
Max Act: 6.5725. Min Act: -0.1700
Data Index: 1335286 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1350. Min Range: -7.1350
Max Act: 6.4475. Min Act: -0.1700
Data Index: 6107252 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1350. Min Range: -7.1350
Max Act: 6.4163. Min Act: -0.1700
Data Index: 7537525 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1350. Min Range: -7.1350
Max Act: 6.3850. Min Act: -0.1700
Data Index: 8453375 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1350. Min Range: -7.1350
Max Act: 6.3538. Min Act: -0.1700
Data Index: 5109267 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1350. Min Range: -7.1350
Max Act: 6.3538. Min Act: -0.1700
Data Index: 4599812 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1350. Min Range: -7.1350
Max Act: 6.3225. Min Act: -0.1700
Data Index: 8134646 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1350. Min Range: -7.1350
Max Act: 6.3225. Min Act: -0.1700
Data Index: 4057366 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1350. Min Range: -7.1350
Max Act: 6.2913. Min Act: -0.1700
Data Index: 3881172 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1350. Min Range: -7.1350
Max Act: 6.2913. Min Act: -0.1700
Data Index: 134035 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1350. Min Range: -7.1350
Max Act: 6.2913. Min Act: -0.1700
Data Index: 7829829 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1350. Min Range: -7.1350
Max Act: 6.2600. Min Act: -0.1700
Data Index: 8452732 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1350. Min Range: -7.1350
Max Act: 6.2600. Min Act: -0.1700
Data Index: 2816241 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1350. Min Range: -7.1350
Max Act: 6.1975. Min Act: -0.1700
Data Index: 5413448 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1350. Min Range: -7.1350
Max Act: 6.1975. Min Act: -0.1700
Data Index: 4112467 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1350. Min Range: -7.1350
Max Act: 6.1975. Min Act: -0.1700
Data Index: 7410772 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19