Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4466 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4723. Min Range: -4.4723
Max Act: 4.4723. Min Act: -0.1700
Data Index: 1593003 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4723. Min Range: -4.4723
Max Act: 4.1911. Min Act: -0.1700
Data Index: 5923792 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4723. Min Range: -4.4723
Max Act: 4.2223. Min Act: -0.1700
Data Index: 815385 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4723. Min Range: -4.4723
Max Act: 4.1286. Min Act: -0.1700
Data Index: 7831900 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4723. Min Range: -4.4723
Max Act: 4.1286. Min Act: -0.1700
Data Index: 4618937 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4723. Min Range: -4.4723
Max Act: 4.1286. Min Act: -0.1700
Data Index: 5109519 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4723. Min Range: -4.4723
Max Act: 4.1286. Min Act: -0.1700
Data Index: 7439546 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4723. Min Range: -4.4723
Max Act: 4.1598. Min Act: -0.1700
Data Index: 6175598 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4723. Min Range: -4.4723
Max Act: 4.0973. Min Act: -0.1700
Data Index: 4813141 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4723. Min Range: -4.4723
Max Act: 4.0973. Min Act: -0.1700
Data Index: 3547697 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4723. Min Range: -4.4723
Max Act: 4.0973. Min Act: -0.1700
Data Index: 3588007 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4723. Min Range: -4.4723
Max Act: 4.0973. Min Act: -0.1700
Data Index: 8043144 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4723. Min Range: -4.4723
Max Act: 4.0348. Min Act: -0.1700
Data Index: 1499118 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4723. Min Range: -4.4723
Max Act: 4.0348. Min Act: -0.1700
Data Index: 4437448 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4723. Min Range: -4.4723
Max Act: 4.0348. Min Act: -0.1700
Data Index: 904121 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4723. Min Range: -4.4723
Max Act: 4.0348. Min Act: -0.1700
Data Index: 5152908 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4723. Min Range: -4.4723
Max Act: 4.0348. Min Act: -0.1700
Data Index: 2499379 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4723. Min Range: -4.4723
Max Act: 4.0035. Min Act: -0.1700
Data Index: 301747 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4723. Min Range: -4.4723
Max Act: 3.9723. Min Act: -0.1700
Data Index: 3157080 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4723. Min Range: -4.4723
Max Act: 3.9723. Min Act: -0.1700
Data Index: 3073228 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19