Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2637 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7499. Min Range: -5.7499
Max Act: 5.7499. Min Act: -0.1700
Data Index: 8335574 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7499. Min Range: -5.7499
Max Act: 5.5624. Min Act: -0.1700
Data Index: 2066471 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7499. Min Range: -5.7499
Max Act: 5.5311. Min Act: -0.1688
Data Index: 7823064 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7499. Min Range: -5.7499
Max Act: 5.4374. Min Act: -0.1700
Data Index: 5892620 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7499. Min Range: -5.7499
Max Act: 5.4374. Min Act: -0.1700
Data Index: 7122336 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7499. Min Range: -5.7499
Max Act: 5.4061. Min Act: -0.1700
Data Index: 6642993 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7499. Min Range: -5.7499
Max Act: 5.3749. Min Act: -0.1700
Data Index: 6686353 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7499. Min Range: -5.7499
Max Act: 5.3749. Min Act: -0.1700
Data Index: 8585169 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7499. Min Range: -5.7499
Max Act: 5.3436. Min Act: -0.1700
Data Index: 7344533 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7499. Min Range: -5.7499
Max Act: 5.3124. Min Act: -0.1700
Data Index: 4944355 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7499. Min Range: -5.7499
Max Act: 5.3124. Min Act: -0.1700
Data Index: 264423 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7499. Min Range: -5.7499
Max Act: 5.3124. Min Act: -0.1700
Data Index: 1108964 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7499. Min Range: -5.7499
Max Act: 5.3124. Min Act: -0.1700
Data Index: 5146672 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7499. Min Range: -5.7499
Max Act: 5.2811. Min Act: -0.1700
Data Index: 593431 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7499. Min Range: -5.7499
Max Act: 5.2811. Min Act: -0.1700
Data Index: 6163539 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7499. Min Range: -5.7499
Max Act: 5.2499. Min Act: -0.1700
Data Index: 2058713 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7499. Min Range: -5.7499
Max Act: 5.2811. Min Act: -0.1700
Data Index: 8369133 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7499. Min Range: -5.7499
Max Act: 5.2499. Min Act: -0.1700
Data Index: 5815643 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7499. Min Range: -5.7499
Max Act: 5.2499. Min Act: -0.1700
Data Index: 1714452 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7499. Min Range: -5.7499
Max Act: 5.2499. Min Act: -0.1700
Data Index: 3784792 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19