Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2838 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9257. Min Range: -5.9257
Max Act: 5.9257. Min Act: -0.1700
Data Index: 7187166 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9257. Min Range: -5.9257
Max Act: 5.7382. Min Act: -0.1700
Data Index: 8376085 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9257. Min Range: -5.9257
Max Act: 5.7382. Min Act: -0.1700
Data Index: 1295644 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9257. Min Range: -5.9257
Max Act: 5.7382. Min Act: -0.1700
Data Index: 2805293 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9257. Min Range: -5.9257
Max Act: 5.7382. Min Act: -0.1700
Data Index: 2203283 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9257. Min Range: -5.9257
Max Act: 5.6132. Min Act: -0.1700
Data Index: 6712412 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9257. Min Range: -5.9257
Max Act: 5.5819. Min Act: -0.1700
Data Index: 4569092 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9257. Min Range: -5.9257
Max Act: 5.5507. Min Act: -0.1700
Data Index: 3078200 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9257. Min Range: -5.9257
Max Act: 5.5194. Min Act: -0.1700
Data Index: 7574336 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9257. Min Range: -5.9257
Max Act: 5.5507. Min Act: -0.1700
Data Index: 3337422 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9257. Min Range: -5.9257
Max Act: 5.5194. Min Act: -0.1700
Data Index: 5063610 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9257. Min Range: -5.9257
Max Act: 5.4882. Min Act: -0.1700
Data Index: 7051682 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9257. Min Range: -5.9257
Max Act: 5.4882. Min Act: -0.1700
Data Index: 8041211 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9257. Min Range: -5.9257
Max Act: 5.5194. Min Act: -0.1700
Data Index: 3426229 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9257. Min Range: -5.9257
Max Act: 5.5194. Min Act: -0.1700
Data Index: 2553679 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9257. Min Range: -5.9257
Max Act: 5.4882. Min Act: -0.1700
Data Index: 8773112 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9257. Min Range: -5.9257
Max Act: 5.4569. Min Act: -0.1700
Data Index: 2987589 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9257. Min Range: -5.9257
Max Act: 5.4882. Min Act: -0.1700
Data Index: 8486299 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9257. Min Range: -5.9257
Max Act: 5.4882. Min Act: -0.1700
Data Index: 1935400 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9257. Min Range: -5.9257
Max Act: 5.4569. Min Act: -0.1700
Data Index: 7453568 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19