Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3485 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3177. Min Range: -5.3177
Max Act: 5.3177. Min Act: -0.1700
Data Index: 843101 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3177. Min Range: -5.3177
Max Act: 5.2865. Min Act: -0.1700
Data Index: 3106507 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3177. Min Range: -5.3177
Max Act: 5.2552. Min Act: -0.1700
Data Index: 488479 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3177. Min Range: -5.3177
Max Act: 5.2552. Min Act: -0.1700
Data Index: 3692448 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3177. Min Range: -5.3177
Max Act: 5.2552. Min Act: -0.1700
Data Index: 2525487 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3177. Min Range: -5.3177
Max Act: 5.2552. Min Act: -0.1700
Data Index: 2208481 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3177. Min Range: -5.3177
Max Act: 5.2552. Min Act: -0.1700
Data Index: 1991377 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3177. Min Range: -5.3177
Max Act: 5.2552. Min Act: -0.1700
Data Index: 3308476 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3177. Min Range: -5.3177
Max Act: 5.2552. Min Act: -0.1700
Data Index: 5217973 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3177. Min Range: -5.3177
Max Act: 5.2240. Min Act: -0.1700
Data Index: 5383283 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3177. Min Range: -5.3177
Max Act: 5.1927. Min Act: -0.1700
Data Index: 6266398 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3177. Min Range: -5.3177
Max Act: 5.2240. Min Act: -0.1700
Data Index: 6463745 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3177. Min Range: -5.3177
Max Act: 5.2240. Min Act: -0.1700
Data Index: 8804010 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3177. Min Range: -5.3177
Max Act: 5.2240. Min Act: -0.1700
Data Index: 4573572 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3177. Min Range: -5.3177
Max Act: 5.1927. Min Act: -0.1700
Data Index: 7558269 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3177. Min Range: -5.3177
Max Act: 5.1927. Min Act: -0.1700
Data Index: 7957259 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3177. Min Range: -5.3177
Max Act: 5.1927. Min Act: -0.1700
Data Index: 2455471 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3177. Min Range: -5.3177
Max Act: 5.1615. Min Act: -0.1700
Data Index: 2628386 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3177. Min Range: -5.3177
Max Act: 5.1927. Min Act: -0.1700
Data Index: 5043641 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3177. Min Range: -5.3177
Max Act: 5.1615. Min Act: -0.1700
Data Index: 3688686 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19