Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4742 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7578. Min Range: -6.7578
Max Act: 6.7578. Min Act: -0.1700
Data Index: 6976703 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7578. Min Range: -6.7578
Max Act: 6.6640. Min Act: -0.1700
Data Index: 3574166 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7578. Min Range: -6.7578
Max Act: 6.6328. Min Act: -0.1700
Data Index: 5551876 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7578. Min Range: -6.7578
Max Act: 6.6015. Min Act: -0.1700
Data Index: 1287892 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7578. Min Range: -6.7578
Max Act: 6.6015. Min Act: -0.1700
Data Index: 8296579 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7578. Min Range: -6.7578
Max Act: 6.5703. Min Act: -0.1700
Data Index: 6951231 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7578. Min Range: -6.7578
Max Act: 6.5390. Min Act: -0.1700
Data Index: 8571122 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7578. Min Range: -6.7578
Max Act: 6.5390. Min Act: -0.1700
Data Index: 2232716 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7578. Min Range: -6.7578
Max Act: 6.5390. Min Act: -0.1700
Data Index: 2940781 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7578. Min Range: -6.7578
Max Act: 6.4765. Min Act: -0.1700
Data Index: 5743527 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7578. Min Range: -6.7578
Max Act: 6.4765. Min Act: -0.1700
Data Index: 8377082 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7578. Min Range: -6.7578
Max Act: 6.4765. Min Act: -0.1700
Data Index: 317999 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7578. Min Range: -6.7578
Max Act: 6.4765. Min Act: -0.1700
Data Index: 6757789 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7578. Min Range: -6.7578
Max Act: 6.4765. Min Act: -0.1700
Data Index: 2535633 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7578. Min Range: -6.7578
Max Act: 6.4765. Min Act: -0.1700
Data Index: 3402644 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7578. Min Range: -6.7578
Max Act: 6.4453. Min Act: -0.1700
Data Index: 987665 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7578. Min Range: -6.7578
Max Act: 6.4140. Min Act: -0.1700
Data Index: 5638304 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7578. Min Range: -6.7578
Max Act: 6.4453. Min Act: -0.1700
Data Index: 5858025 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7578. Min Range: -6.7578
Max Act: 6.4453. Min Act: -0.1700
Data Index: 3229216 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7578. Min Range: -6.7578
Max Act: 6.4453. Min Act: -0.1700
Data Index: 5837541 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19