Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5787 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0174. Min Range: -5.0174
Max Act: 5.0174. Min Act: -0.1700
Data Index: 256540 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0174. Min Range: -5.0174
Max Act: 4.9236. Min Act: -0.1700
Data Index: 4489204 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0174. Min Range: -5.0174
Max Act: 4.8924. Min Act: -0.1700
Data Index: 829402 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0174. Min Range: -5.0174
Max Act: 4.8611. Min Act: -0.1700
Data Index: 6670447 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0174. Min Range: -5.0174
Max Act: 4.8299. Min Act: -0.1700
Data Index: 6962753 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0174. Min Range: -5.0174
Max Act: 4.8611. Min Act: -0.1700
Data Index: 360976 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0174. Min Range: -5.0174
Max Act: 4.7986. Min Act: -0.1700
Data Index: 316321 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0174. Min Range: -5.0174
Max Act: 4.7674. Min Act: -0.1700
Data Index: 4489199 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0174. Min Range: -5.0174
Max Act: 4.7674. Min Act: -0.1700
Data Index: 1490835 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0174. Min Range: -5.0174
Max Act: 4.7986. Min Act: -0.1700
Data Index: 4028555 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0174. Min Range: -5.0174
Max Act: 4.7361. Min Act: -0.1700
Data Index: 1393158 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0174. Min Range: -5.0174
Max Act: 4.7674. Min Act: -0.1700
Data Index: 4381164 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0174. Min Range: -5.0174
Max Act: 4.7361. Min Act: -0.1700
Data Index: 1819844 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0174. Min Range: -5.0174
Max Act: 4.7361. Min Act: -0.1700
Data Index: 7427182 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0174. Min Range: -5.0174
Max Act: 4.7049. Min Act: -0.1700
Data Index: 1961652 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0174. Min Range: -5.0174
Max Act: 4.7049. Min Act: -0.1700
Data Index: 6670446 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0174. Min Range: -5.0174
Max Act: 4.7049. Min Act: -0.1700
Data Index: 1218901 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0174. Min Range: -5.0174
Max Act: 4.7361. Min Act: -0.1700
Data Index: 3984241 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0174. Min Range: -5.0174
Max Act: 4.7049. Min Act: -0.1700
Data Index: 2977138 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0174. Min Range: -5.0174
Max Act: 4.7049. Min Act: -0.1700
Data Index: 2727365 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19