Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3772 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7001. Min Range: -5.7001
Max Act: 5.6689. Min Act: -0.1700
Data Index: 5181073 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7001. Min Range: -5.7001
Max Act: 5.7001. Min Act: -0.1700
Data Index: 2841004 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7001. Min Range: -5.7001
Max Act: 5.5751. Min Act: -0.1700
Data Index: 8638935 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7001. Min Range: -5.7001
Max Act: 5.5126. Min Act: -0.1700
Data Index: 8324353 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7001. Min Range: -5.7001
Max Act: 5.4814. Min Act: -0.1700
Data Index: 1162218 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7001. Min Range: -5.7001
Max Act: 5.4814. Min Act: -0.1700
Data Index: 3164230 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7001. Min Range: -5.7001
Max Act: 5.4501. Min Act: -0.1700
Data Index: 137768 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7001. Min Range: -5.7001
Max Act: 5.4501. Min Act: -0.1700
Data Index: 488245 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7001. Min Range: -5.7001
Max Act: 5.4501. Min Act: -0.1700
Data Index: 3080622 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7001. Min Range: -5.7001
Max Act: 5.3876. Min Act: -0.1700
Data Index: 4660568 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7001. Min Range: -5.7001
Max Act: 5.3876. Min Act: -0.1700
Data Index: 7105643 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7001. Min Range: -5.7001
Max Act: 5.3564. Min Act: -0.1700
Data Index: 7832697 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7001. Min Range: -5.7001
Max Act: 5.3564. Min Act: -0.1700
Data Index: 478057 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7001. Min Range: -5.7001
Max Act: 5.3564. Min Act: -0.1700
Data Index: 6983151 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7001. Min Range: -5.7001
Max Act: 5.3251. Min Act: -0.1700
Data Index: 6116234 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7001. Min Range: -5.7001
Max Act: 5.3251. Min Act: -0.1700
Data Index: 6805532 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7001. Min Range: -5.7001
Max Act: 5.3251. Min Act: -0.1700
Data Index: 7172827 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7001. Min Range: -5.7001
Max Act: 5.3251. Min Act: -0.1700
Data Index: 6404678 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7001. Min Range: -5.7001
Max Act: 5.2939. Min Act: -0.1700
Data Index: 2534339 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7001. Min Range: -5.7001
Max Act: 5.2626. Min Act: -0.1700
Data Index: 3850292 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19