Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5304 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2535. Min Range: -6.2535
Max Act: 6.2535. Min Act: -0.1700
Data Index: 7042057 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2535. Min Range: -6.2535
Max Act: 6.1910. Min Act: -0.1700
Data Index: 2762888 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2535. Min Range: -6.2535
Max Act: 5.9097. Min Act: -0.1700
Data Index: 7271614 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2535. Min Range: -6.2535
Max Act: 5.8785. Min Act: -0.1700
Data Index: 1345026 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2535. Min Range: -6.2535
Max Act: 5.9097. Min Act: -0.1700
Data Index: 4824149 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2535. Min Range: -6.2535
Max Act: 5.8472. Min Act: -0.1700
Data Index: 6023384 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2535. Min Range: -6.2535
Max Act: 5.8472. Min Act: -0.1700
Data Index: 1272918 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2535. Min Range: -6.2535
Max Act: 5.8160. Min Act: -0.1700
Data Index: 5913306 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2535. Min Range: -6.2535
Max Act: 5.8160. Min Act: -0.1700
Data Index: 5618068 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2535. Min Range: -6.2535
Max Act: 5.8160. Min Act: -0.1700
Data Index: 1028404 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2535. Min Range: -6.2535
Max Act: 5.7847. Min Act: -0.1700
Data Index: 6087394 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2535. Min Range: -6.2535
Max Act: 5.7847. Min Act: -0.1700
Data Index: 7576364 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2535. Min Range: -6.2535
Max Act: 5.7847. Min Act: -0.1700
Data Index: 4020054 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2535. Min Range: -6.2535
Max Act: 5.7535. Min Act: -0.1700
Data Index: 5805182 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2535. Min Range: -6.2535
Max Act: 5.7222. Min Act: -0.1700
Data Index: 2121817 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2535. Min Range: -6.2535
Max Act: 5.7222. Min Act: -0.1700
Data Index: 3411583 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2535. Min Range: -6.2535
Max Act: 5.7222. Min Act: -0.1700
Data Index: 4990237 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2535. Min Range: -6.2535
Max Act: 5.7222. Min Act: -0.1700
Data Index: 803112 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2535. Min Range: -6.2535
Max Act: 5.7222. Min Act: -0.1700
Data Index: 5116185 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2535. Min Range: -6.2535
Max Act: 5.7222. Min Act: -0.1700
Data Index: 4142533 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19