Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3317 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2096. Min Range: -7.2096
Max Act: 7.2096. Min Act: -0.1700
Data Index: 2930736 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2096. Min Range: -7.2096
Max Act: 7.1784. Min Act: -0.1700
Data Index: 4253040 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2096. Min Range: -7.2096
Max Act: 7.0846. Min Act: -0.1700
Data Index: 267664 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2096. Min Range: -7.2096
Max Act: 7.1159. Min Act: -0.1700
Data Index: 6855442 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2096. Min Range: -7.2096
Max Act: 7.0846. Min Act: -0.1700
Data Index: 763617 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2096. Min Range: -7.2096
Max Act: 7.0221. Min Act: -0.1700
Data Index: 2233473 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.9284. Min Act: -0.1700
Data Index: 4839089 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.9284. Min Act: -0.1700
Data Index: 648468 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.8971. Min Act: -0.1700
Data Index: 3210672 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.8971. Min Act: -0.1700
Data Index: 7096240 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.8034. Min Act: -0.1700
Data Index: 3547084 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.8034. Min Act: -0.1700
Data Index: 7459440 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.8034. Min Act: -0.1700
Data Index: 6180245 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.8034. Min Act: -0.1700
Data Index: 8140541 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.7721. Min Act: -0.1700
Data Index: 3586211 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.7721. Min Act: -0.1700
Data Index: 1433915 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.7721. Min Act: -0.1700
Data Index: 547435 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.7409. Min Act: -0.1700
Data Index: 8002778 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.7096. Min Act: -0.1700
Data Index: 6779969 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2096. Min Range: -7.2096
Max Act: 6.7409. Min Act: -0.1700
Data Index: 8767745 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19