Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4423 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3325. Min Range: -6.3325
Max Act: 6.3325. Min Act: -0.1700
Data Index: 8606183 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3325. Min Range: -6.3325
Max Act: 6.2388. Min Act: -0.1700
Data Index: 282303 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3325. Min Range: -6.3325
Max Act: 5.8325. Min Act: -0.1700
Data Index: 430785 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3325. Min Range: -6.3325
Max Act: 5.8325. Min Act: -0.1700
Data Index: 7293034 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3325. Min Range: -6.3325
Max Act: 5.8013. Min Act: -0.1700
Data Index: 282308 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3325. Min Range: -6.3325
Max Act: 5.8013. Min Act: -0.1700
Data Index: 8017263 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3325. Min Range: -6.3325
Max Act: 5.7700. Min Act: -0.1700
Data Index: 3401873 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3325. Min Range: -6.3325
Max Act: 5.7388. Min Act: -0.1700
Data Index: 6639873 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3325. Min Range: -6.3325
Max Act: 5.7700. Min Act: -0.1700
Data Index: 7241494 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3325. Min Range: -6.3325
Max Act: 5.7388. Min Act: -0.1700
Data Index: 555438 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3325. Min Range: -6.3325
Max Act: 5.6763. Min Act: -0.1700
Data Index: 3120893 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3325. Min Range: -6.3325
Max Act: 5.6763. Min Act: -0.1700
Data Index: 2876771 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3325. Min Range: -6.3325
Max Act: 5.6763. Min Act: -0.1700
Data Index: 3245559 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3325. Min Range: -6.3325
Max Act: 5.6450. Min Act: -0.1700
Data Index: 352102 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3325. Min Range: -6.3325
Max Act: 5.6450. Min Act: -0.1700
Data Index: 8438504 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3325. Min Range: -6.3325
Max Act: 5.6450. Min Act: -0.1700
Data Index: 4388144 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3325. Min Range: -6.3325
Max Act: 5.6450. Min Act: -0.1700
Data Index: 8637940 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3325. Min Range: -6.3325
Max Act: 5.6138. Min Act: -0.1700
Data Index: 2483317 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3325. Min Range: -6.3325
Max Act: 5.5825. Min Act: -0.1700
Data Index: 7782047 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3325. Min Range: -6.3325
Max Act: 5.5825. Min Act: -0.1700
Data Index: 727747 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19