Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 455 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2347. Min Range: -5.2347
Max Act: 5.2347. Min Act: -0.1700
Data Index: 4166239 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2347. Min Range: -5.2347
Max Act: 5.0785. Min Act: -0.1700
Data Index: 1991593 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2347. Min Range: -5.2347
Max Act: 5.0785. Min Act: -0.1700
Data Index: 5691190 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2347. Min Range: -5.2347
Max Act: 5.0472. Min Act: -0.1700
Data Index: 1133588 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2347. Min Range: -5.2347
Max Act: 5.0160. Min Act: -0.1700
Data Index: 5022882 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2347. Min Range: -5.2347
Max Act: 4.9535. Min Act: -0.1700
Data Index: 645499 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2347. Min Range: -5.2347
Max Act: 4.8597. Min Act: -0.1700
Data Index: 3443125 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2347. Min Range: -5.2347
Max Act: 4.8597. Min Act: -0.1700
Data Index: 257955 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2347. Min Range: -5.2347
Max Act: 4.8597. Min Act: -0.1700
Data Index: 6333792 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2347. Min Range: -5.2347
Max Act: 4.8597. Min Act: -0.1700
Data Index: 3042809 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2347. Min Range: -5.2347
Max Act: 4.8285. Min Act: -0.1700
Data Index: 4989632 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2347. Min Range: -5.2347
Max Act: 4.7660. Min Act: -0.1700
Data Index: 1357207 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2347. Min Range: -5.2347
Max Act: 4.7972. Min Act: -0.1700
Data Index: 5110166 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2347. Min Range: -5.2347
Max Act: 4.7347. Min Act: -0.1700
Data Index: 81187 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2347. Min Range: -5.2347
Max Act: 4.7035. Min Act: -0.1700
Data Index: 4978715 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2347. Min Range: -5.2347
Max Act: 4.7035. Min Act: -0.1700
Data Index: 4258737 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2347. Min Range: -5.2347
Max Act: 4.6722. Min Act: -0.1700
Data Index: 575528 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2347. Min Range: -5.2347
Max Act: 4.6722. Min Act: -0.1700
Data Index: 3423008 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2347. Min Range: -5.2347
Max Act: 4.6722. Min Act: -0.1700
Data Index: 8385068 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2347. Min Range: -5.2347
Max Act: 4.6410. Min Act: -0.1700
Data Index: 2470735 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19