Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2421 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4993. Min Range: -7.4993
Max Act: 7.4993. Min Act: -0.1700
Data Index: 4276805 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4993. Min Range: -7.4993
Max Act: 7.3743. Min Act: -0.1700
Data Index: 2559719 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4993. Min Range: -7.4993
Max Act: 7.0930. Min Act: -0.1700
Data Index: 6992447 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4993. Min Range: -7.4993
Max Act: 7.0618. Min Act: -0.1700
Data Index: 2039103 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4993. Min Range: -7.4993
Max Act: 6.9993. Min Act: -0.1700
Data Index: 6638145 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4993. Min Range: -7.4993
Max Act: 7.0305. Min Act: -0.1700
Data Index: 205670 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4993. Min Range: -7.4993
Max Act: 6.9680. Min Act: -0.1700
Data Index: 2783373 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4993. Min Range: -7.4993
Max Act: 6.9368. Min Act: -0.1700
Data Index: 5538846 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4993. Min Range: -7.4993
Max Act: 6.9055. Min Act: -0.1700
Data Index: 2151678 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4993. Min Range: -7.4993
Max Act: 6.9055. Min Act: -0.1700
Data Index: 120149 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4993. Min Range: -7.4993
Max Act: 6.8430. Min Act: -0.1700
Data Index: 3150462 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4993. Min Range: -7.4993
Max Act: 6.8743. Min Act: -0.1700
Data Index: 5270777 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4993. Min Range: -7.4993
Max Act: 6.8118. Min Act: -0.1700
Data Index: 8102784 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4993. Min Range: -7.4993
Max Act: 6.7805. Min Act: -0.1700
Data Index: 2401893 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4993. Min Range: -7.4993
Max Act: 6.7493. Min Act: -0.1700
Data Index: 4324270 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4993. Min Range: -7.4993
Max Act: 6.7493. Min Act: -0.1700
Data Index: 5465539 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4993. Min Range: -7.4993
Max Act: 6.7493. Min Act: -0.1700
Data Index: 6094645 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4993. Min Range: -7.4993
Max Act: 6.7493. Min Act: -0.1700
Data Index: 3437595 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4993. Min Range: -7.4993
Max Act: 6.7180. Min Act: -0.1700
Data Index: 7316546 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4993. Min Range: -7.4993
Max Act: 6.6868. Min Act: -0.1700
Data Index: 7709132 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19