Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4325 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6876. Min Range: -4.6876
Max Act: 4.6876. Min Act: -0.1700
Data Index: 3019131 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6876. Min Range: -4.6876
Max Act: 4.6251. Min Act: -0.1700
Data Index: 4468790 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6876. Min Range: -4.6876
Max Act: 4.5314. Min Act: -0.1700
Data Index: 667763 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6876. Min Range: -4.6876
Max Act: 4.4689. Min Act: -0.1700
Data Index: 7014331 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6876. Min Range: -4.6876
Max Act: 4.4689. Min Act: -0.1700
Data Index: 4163354 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6876. Min Range: -4.6876
Max Act: 4.4376. Min Act: -0.1700
Data Index: 3036639 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6876. Min Range: -4.6876
Max Act: 4.4376. Min Act: -0.1700
Data Index: 6403082 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6876. Min Range: -4.6876
Max Act: 4.4064. Min Act: -0.1700
Data Index: 667752 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6876. Min Range: -4.6876
Max Act: 4.3439. Min Act: -0.1700
Data Index: 6980800 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6876. Min Range: -4.6876
Max Act: 4.3439. Min Act: -0.1700
Data Index: 667753 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6876. Min Range: -4.6876
Max Act: 4.3439. Min Act: -0.1700
Data Index: 346760 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6876. Min Range: -4.6876
Max Act: 4.3126. Min Act: -0.1700
Data Index: 667762 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6876. Min Range: -4.6876
Max Act: 4.2814. Min Act: -0.1700
Data Index: 312057 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6876. Min Range: -4.6876
Max Act: 4.2814. Min Act: -0.1700
Data Index: 7569553 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6876. Min Range: -4.6876
Max Act: 4.3126. Min Act: -0.1700
Data Index: 7569554 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6876. Min Range: -4.6876
Max Act: 4.2814. Min Act: -0.1700
Data Index: 8311225 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6876. Min Range: -4.6876
Max Act: 4.2501. Min Act: -0.1700
Data Index: 1723706 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6876. Min Range: -4.6876
Max Act: 4.2501. Min Act: -0.1700
Data Index: 658851 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6876. Min Range: -4.6876
Max Act: 4.2501. Min Act: -0.1700
Data Index: 4631608 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6876. Min Range: -4.6876
Max Act: 4.2189. Min Act: -0.1700
Data Index: 8367425 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19