Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5519 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4248. Min Range: -9.4248
Max Act: 9.4248. Min Act: -0.1700
Data Index: 831 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4248. Min Range: -9.4248
Max Act: 9.2998. Min Act: -0.1699
Data Index: 151118 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4248. Min Range: -9.4248
Max Act: 9.2373. Min Act: -0.1700
Data Index: 6151895 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4248. Min Range: -9.4248
Max Act: 9.1123. Min Act: -0.1700
Data Index: 8035797 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4248. Min Range: -9.4248
Max Act: 9.1123. Min Act: -0.1700
Data Index: 4149786 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4248. Min Range: -9.4248
Max Act: 9.1123. Min Act: -0.1700
Data Index: 5696978 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4248. Min Range: -9.4248
Max Act: 9.0498. Min Act: -0.1700
Data Index: 1921465 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4248. Min Range: -9.4248
Max Act: 8.9873. Min Act: -0.1700
Data Index: 341914 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4248. Min Range: -9.4248
Max Act: 8.8623. Min Act: -0.1700
Data Index: 402271 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4248. Min Range: -9.4248
Max Act: 8.8623. Min Act: -0.1700
Data Index: 7733803 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4248. Min Range: -9.4248
Max Act: 8.8623. Min Act: -0.1700
Data Index: 1057162 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4248. Min Range: -9.4248
Max Act: 8.7998. Min Act: -0.1700
Data Index: 7883753 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4248. Min Range: -9.4248
Max Act: 8.7998. Min Act: -0.1700
Data Index: 936620 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4248. Min Range: -9.4248
Max Act: 8.8623. Min Act: -0.1700
Data Index: 5955383 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4248. Min Range: -9.4248
Max Act: 8.7998. Min Act: -0.1700
Data Index: 3216254 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4248. Min Range: -9.4248
Max Act: 8.7373. Min Act: -0.1700
Data Index: 6240610 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4248. Min Range: -9.4248
Max Act: 8.7373. Min Act: -0.1700
Data Index: 5241313 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4248. Min Range: -9.4248
Max Act: 8.7373. Min Act: -0.1700
Data Index: 4423261 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4248. Min Range: -9.4248
Max Act: 8.7373. Min Act: -0.1700
Data Index: 4386570 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4248. Min Range: -9.4248
Max Act: 8.7373. Min Act: -0.1700
Data Index: 8042523 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19