Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3176 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2554. Min Range: -6.2554
Max Act: 6.2554. Min Act: -0.1700
Data Index: 4778149 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2554. Min Range: -6.2554
Max Act: 6.0367. Min Act: -0.1700
Data Index: 7406187 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2554. Min Range: -6.2554
Max Act: 5.9117. Min Act: -0.1700
Data Index: 5549577 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2554. Min Range: -6.2554
Max Act: 5.9117. Min Act: -0.1700
Data Index: 1562820 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2554. Min Range: -6.2554
Max Act: 5.8804. Min Act: -0.1700
Data Index: 5782857 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2554. Min Range: -6.2554
Max Act: 5.8804. Min Act: -0.1700
Data Index: 5175573 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2554. Min Range: -6.2554
Max Act: 5.8492. Min Act: -0.1700
Data Index: 2572821 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2554. Min Range: -6.2554
Max Act: 5.8492. Min Act: -0.1700
Data Index: 299335 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2554. Min Range: -6.2554
Max Act: 5.8492. Min Act: -0.1700
Data Index: 810519 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2554. Min Range: -6.2554
Max Act: 5.8179. Min Act: -0.1700
Data Index: 8637989 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2554. Min Range: -6.2554
Max Act: 5.7867. Min Act: -0.1700
Data Index: 8169383 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2554. Min Range: -6.2554
Max Act: 5.7867. Min Act: -0.1700
Data Index: 6221684 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2554. Min Range: -6.2554
Max Act: 5.7554. Min Act: -0.1700
Data Index: 2383835 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2554. Min Range: -6.2554
Max Act: 5.7554. Min Act: -0.1700
Data Index: 5995452 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2554. Min Range: -6.2554
Max Act: 5.6929. Min Act: -0.1700
Data Index: 2094773 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2554. Min Range: -6.2554
Max Act: 5.7242. Min Act: -0.1700
Data Index: 853181 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2554. Min Range: -6.2554
Max Act: 5.6929. Min Act: -0.1700
Data Index: 5197873 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2554. Min Range: -6.2554
Max Act: 5.6617. Min Act: -0.1700
Data Index: 5162415 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2554. Min Range: -6.2554
Max Act: 5.6617. Min Act: -0.1700
Data Index: 1713072 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2554. Min Range: -6.2554
Max Act: 5.6304. Min Act: -0.1700
Data Index: 1684367 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19