Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 761 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8390. Min Range: -6.8390
Max Act: 6.8390. Min Act: -0.1700
Data Index: 6627051 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8390. Min Range: -6.8390
Max Act: 6.6828. Min Act: -0.1700
Data Index: 5880937 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8390. Min Range: -6.8390
Max Act: 6.5890. Min Act: -0.1700
Data Index: 5032170 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8390. Min Range: -6.8390
Max Act: 6.5578. Min Act: -0.1700
Data Index: 2824044 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8390. Min Range: -6.8390
Max Act: 6.4953. Min Act: -0.1700
Data Index: 8809203 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8390. Min Range: -6.8390
Max Act: 6.4953. Min Act: -0.1700
Data Index: 6039367 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8390. Min Range: -6.8390
Max Act: 6.4640. Min Act: -0.1700
Data Index: 7774520 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8390. Min Range: -6.8390
Max Act: 6.4640. Min Act: -0.1700
Data Index: 1223021 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8390. Min Range: -6.8390
Max Act: 6.4328. Min Act: -0.1700
Data Index: 1594728 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8390. Min Range: -6.8390
Max Act: 6.4015. Min Act: -0.1700
Data Index: 2816645 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8390. Min Range: -6.8390
Max Act: 6.3703. Min Act: -0.1700
Data Index: 2067715 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8390. Min Range: -6.8390
Max Act: 6.3703. Min Act: -0.1700
Data Index: 3386670 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8390. Min Range: -6.8390
Max Act: 6.4328. Min Act: -0.1700
Data Index: 8379233 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8390. Min Range: -6.8390
Max Act: 6.3703. Min Act: -0.1700
Data Index: 8598808 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8390. Min Range: -6.8390
Max Act: 6.3078. Min Act: -0.1700
Data Index: 2667675 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8390. Min Range: -6.8390
Max Act: 6.3078. Min Act: -0.1700
Data Index: 2506678 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8390. Min Range: -6.8390
Max Act: 6.3078. Min Act: -0.1700
Data Index: 6725302 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8390. Min Range: -6.8390
Max Act: 6.3078. Min Act: -0.1700
Data Index: 7453059 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8390. Min Range: -6.8390
Max Act: 6.3078. Min Act: -0.1700
Data Index: 4086053 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8390. Min Range: -6.8390
Max Act: 6.3078. Min Act: -0.1700
Data Index: 1084644 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19