Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2393 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.8189. Min Act: -0.1700
Data Index: 2431667 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.6627. Min Act: -0.1700
Data Index: 2677088 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.6314. Min Act: -0.1700
Data Index: 365818 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.6002. Min Act: -0.1700
Data Index: 5024858 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.4752. Min Act: -0.1700
Data Index: 1492887 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.4439. Min Act: -0.1700
Data Index: 6151727 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.4127. Min Act: -0.1700
Data Index: 643685 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.4127. Min Act: -0.1700
Data Index: 7731496 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.3814. Min Act: -0.1700
Data Index: 1742835 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.3502. Min Act: -0.1700
Data Index: 5828912 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.3502. Min Act: -0.1700
Data Index: 932323 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.3502. Min Act: -0.1700
Data Index: 1552652 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.3502. Min Act: -0.1700
Data Index: 4260266 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.3189. Min Act: -0.1700
Data Index: 1463380 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.3502. Min Act: -0.1700
Data Index: 651661 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.3502. Min Act: -0.1700
Data Index: 8506673 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.2877. Min Act: -0.1700
Data Index: 7282526 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.3189. Min Act: -0.1700
Data Index: 186066 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.3189. Min Act: -0.1700
Data Index: 7256146 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.3189. Min Act: -0.1700
Data Index: 5024864 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19