Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3505 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8538. Min Range: -8.8538
Max Act: 8.8538. Min Act: -0.1700
Data Index: 6347082 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8538. Min Range: -8.8538
Max Act: 8.4163. Min Act: -0.1700
Data Index: 2043465 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8538. Min Range: -8.8538
Max Act: 8.4163. Min Act: -0.1700
Data Index: 4605236 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8538. Min Range: -8.8538
Max Act: 8.2913. Min Act: -0.1700
Data Index: 3514509 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8538. Min Range: -8.8538
Max Act: 8.2913. Min Act: -0.1700
Data Index: 8298571 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8538. Min Range: -8.8538
Max Act: 8.2913. Min Act: -0.1700
Data Index: 1489188 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8538. Min Range: -8.8538
Max Act: 8.2288. Min Act: -0.1700
Data Index: 2600934 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8538. Min Range: -8.8538
Max Act: 8.1038. Min Act: -0.1700
Data Index: 8380137 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8538. Min Range: -8.8538
Max Act: 8.0413. Min Act: -0.1700
Data Index: 8380139 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8538. Min Range: -8.8538
Max Act: 7.9163. Min Act: -0.1700
Data Index: 5317174 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8538. Min Range: -8.8538
Max Act: 7.9163. Min Act: -0.1700
Data Index: 6318558 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8538. Min Range: -8.8538
Max Act: 7.8538. Min Act: -0.1700
Data Index: 6216919 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8538. Min Range: -8.8538
Max Act: 7.9163. Min Act: -0.1700
Data Index: 8606780 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8538. Min Range: -8.8538
Max Act: 7.7913. Min Act: -0.1700
Data Index: 3359965 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8538. Min Range: -8.8538
Max Act: 7.7913. Min Act: -0.1700
Data Index: 5318520 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8538. Min Range: -8.8538
Max Act: 7.7913. Min Act: -0.1700
Data Index: 5909588 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8538. Min Range: -8.8538
Max Act: 7.7288. Min Act: -0.1700
Data Index: 7038197 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8538. Min Range: -8.8538
Max Act: 7.6663. Min Act: -0.1700
Data Index: 8561618 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8538. Min Range: -8.8538
Max Act: 7.6351. Min Act: -0.1700
Data Index: 6986661 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8538. Min Range: -8.8538
Max Act: 7.6351. Min Act: -0.1700
Data Index: 4007927 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19