Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3772 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4143. Min Range: -7.4143
Max Act: 7.4143. Min Act: -0.1700
Data Index: 7988773 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4143. Min Range: -7.4143
Max Act: 7.1018. Min Act: -0.1700
Data Index: 1006681 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4143. Min Range: -7.4143
Max Act: 7.0706. Min Act: -0.1700
Data Index: 801705 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4143. Min Range: -7.4143
Max Act: 6.9456. Min Act: -0.1700
Data Index: 550925 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4143. Min Range: -7.4143
Max Act: 6.8518. Min Act: -0.1700
Data Index: 1279473 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4143. Min Range: -7.4143
Max Act: 6.8206. Min Act: -0.1700
Data Index: 1522459 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4143. Min Range: -7.4143
Max Act: 6.7581. Min Act: -0.1700
Data Index: 8731013 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4143. Min Range: -7.4143
Max Act: 6.6956. Min Act: -0.1700
Data Index: 7989380 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4143. Min Range: -7.4143
Max Act: 6.6643. Min Act: -0.1700
Data Index: 5570636 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4143. Min Range: -7.4143
Max Act: 6.7268. Min Act: -0.1700
Data Index: 1370689 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4143. Min Range: -7.4143
Max Act: 6.6956. Min Act: -0.1700
Data Index: 5860109 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4143. Min Range: -7.4143
Max Act: 6.6956. Min Act: -0.1700
Data Index: 8780075 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4143. Min Range: -7.4143
Max Act: 6.6331. Min Act: -0.1700
Data Index: 4190628 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4143. Min Range: -7.4143
Max Act: 6.6643. Min Act: -0.1700
Data Index: 32563 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4143. Min Range: -7.4143
Max Act: 6.6018. Min Act: -0.1700
Data Index: 1501488 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4143. Min Range: -7.4143
Max Act: 6.6018. Min Act: -0.1700
Data Index: 4719448 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4143. Min Range: -7.4143
Max Act: 6.6018. Min Act: -0.1700
Data Index: 238310 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4143. Min Range: -7.4143
Max Act: 6.6331. Min Act: -0.1700
Data Index: 6922164 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4143. Min Range: -7.4143
Max Act: 6.6331. Min Act: -0.1700
Data Index: 3717665 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4143. Min Range: -7.4143
Max Act: 6.5706. Min Act: -0.1700
Data Index: 3845988 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19