Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2855 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.6348. Min Act: -0.1700
Data Index: 3294529 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.4786. Min Act: -0.1700
Data Index: 2394230 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.4786. Min Act: -0.1700
Data Index: 1554705 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.4161. Min Act: -0.1700
Data Index: 4069965 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.4161. Min Act: -0.1700
Data Index: 4883519 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.4161. Min Act: -0.1700
Data Index: 3590953 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.3536. Min Act: -0.1700
Data Index: 3254626 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.3223. Min Act: -0.1700
Data Index: 1301537 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.3223. Min Act: -0.1700
Data Index: 1301536 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.3223. Min Act: -0.1700
Data Index: 2394229 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.3223. Min Act: -0.1700
Data Index: 7115519 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.2911. Min Act: -0.1700
Data Index: 6486144 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.1973. Min Act: -0.1700
Data Index: 3128275 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.1973. Min Act: -0.1700
Data Index: 8720171 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.1661. Min Act: -0.1700
Data Index: 2850814 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.1661. Min Act: -0.1700
Data Index: 6565935 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.1036. Min Act: -0.1700
Data Index: 6255258 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.1348. Min Act: -0.1700
Data Index: 6565933 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.1348. Min Act: -0.1700
Data Index: 1446683 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6348. Min Range: -6.6348
Max Act: 6.1036. Min Act: -0.1700
Data Index: 6672769 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19