Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3498 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4124. Min Range: -6.4124
Max Act: 6.4124. Min Act: -0.1700
Data Index: 6250413 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4124. Min Range: -6.4124
Max Act: 6.2874. Min Act: -0.1700
Data Index: 8796031 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4124. Min Range: -6.4124
Max Act: 6.1624. Min Act: -0.1700
Data Index: 7989479 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4124. Min Range: -6.4124
Max Act: 6.0999. Min Act: -0.1700
Data Index: 7126550 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4124. Min Range: -6.4124
Max Act: 6.0686. Min Act: -0.1700
Data Index: 2793894 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4124. Min Range: -6.4124
Max Act: 6.0374. Min Act: -0.1700
Data Index: 2391606 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4124. Min Range: -6.4124
Max Act: 5.9749. Min Act: -0.1700
Data Index: 637523 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4124. Min Range: -6.4124
Max Act: 5.8811. Min Act: -0.1700
Data Index: 376443 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4124. Min Range: -6.4124
Max Act: 5.8811. Min Act: -0.1700
Data Index: 2043550 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4124. Min Range: -6.4124
Max Act: 5.8499. Min Act: -0.1700
Data Index: 5093335 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4124. Min Range: -6.4124
Max Act: 5.8499. Min Act: -0.1700
Data Index: 4066634 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4124. Min Range: -6.4124
Max Act: 5.8186. Min Act: -0.1700
Data Index: 7784437 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4124. Min Range: -6.4124
Max Act: 5.8499. Min Act: -0.1700
Data Index: 5665478 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4124. Min Range: -6.4124
Max Act: 5.8186. Min Act: -0.1700
Data Index: 1455352 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4124. Min Range: -6.4124
Max Act: 5.7561. Min Act: -0.1700
Data Index: 5351033 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4124. Min Range: -6.4124
Max Act: 5.7561. Min Act: -0.1700
Data Index: 2153541 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4124. Min Range: -6.4124
Max Act: 5.7249. Min Act: -0.1700
Data Index: 7381816 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4124. Min Range: -6.4124
Max Act: 5.6311. Min Act: -0.1700
Data Index: 5773582 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4124. Min Range: -6.4124
Max Act: 5.6624. Min Act: -0.1700
Data Index: 5529180 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4124. Min Range: -6.4124
Max Act: 5.5999. Min Act: -0.1700
Data Index: 5163191 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19