Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2889 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0053. Min Range: -6.0053
Max Act: 6.0053. Min Act: -0.1700
Data Index: 8397965 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0053. Min Range: -6.0053
Max Act: 5.8178. Min Act: -0.1700
Data Index: 1206875 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0053. Min Range: -6.0053
Max Act: 5.7865. Min Act: -0.1700
Data Index: 1585793 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0053. Min Range: -6.0053
Max Act: 5.5053. Min Act: -0.1700
Data Index: 5303403 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0053. Min Range: -6.0053
Max Act: 5.4740. Min Act: -0.1700
Data Index: 7345110 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0053. Min Range: -6.0053
Max Act: 5.4428. Min Act: -0.1700
Data Index: 4727076 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0053. Min Range: -6.0053
Max Act: 5.4740. Min Act: -0.1700
Data Index: 7599577 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0053. Min Range: -6.0053
Max Act: 5.4740. Min Act: -0.1700
Data Index: 2268605 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0053. Min Range: -6.0053
Max Act: 5.4115. Min Act: -0.1700
Data Index: 7836568 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0053. Min Range: -6.0053
Max Act: 5.4428. Min Act: -0.1700
Data Index: 5745676 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0053. Min Range: -6.0053
Max Act: 5.4428. Min Act: -0.1700
Data Index: 1985218 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0053. Min Range: -6.0053
Max Act: 5.4428. Min Act: -0.1700
Data Index: 8763251 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0053. Min Range: -6.0053
Max Act: 5.4115. Min Act: -0.1700
Data Index: 3403929 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0053. Min Range: -6.0053
Max Act: 5.4115. Min Act: -0.1700
Data Index: 8150417 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0053. Min Range: -6.0053
Max Act: 5.4115. Min Act: -0.1700
Data Index: 2984422 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0053. Min Range: -6.0053
Max Act: 5.4428. Min Act: -0.1700
Data Index: 106159 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0053. Min Range: -6.0053
Max Act: 5.3803. Min Act: -0.1700
Data Index: 5441208 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0053. Min Range: -6.0053
Max Act: 5.3803. Min Act: -0.1700
Data Index: 5548081 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0053. Min Range: -6.0053
Max Act: 5.3178. Min Act: -0.1700
Data Index: 6063523 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0053. Min Range: -6.0053
Max Act: 5.3490. Min Act: -0.1700
Data Index: 7258470 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19