Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2344 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.8570. Min Act: -0.1700
Data Index: 8482521 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7945. Min Act: -0.1700
Data Index: 6935095 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.8258. Min Act: -0.1700
Data Index: 1234474 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7945. Min Act: -0.1700
Data Index: 1921626 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7633. Min Act: -0.1700
Data Index: 5413509 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7320. Min Act: -0.1700
Data Index: 4089293 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7320. Min Act: -0.1700
Data Index: 7292933 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7320. Min Act: -0.1700
Data Index: 3256571 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7008. Min Act: -0.1700
Data Index: 7874561 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7008. Min Act: -0.1700
Data Index: 8134115 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7008. Min Act: -0.1700
Data Index: 1201461 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7008. Min Act: -0.1700
Data Index: 4141775 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7008. Min Act: -0.1700
Data Index: 4136449 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7008. Min Act: -0.1700
Data Index: 1520184 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.7008. Min Act: -0.1700
Data Index: 6482074 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.6695. Min Act: -0.1700
Data Index: 7731094 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.6695. Min Act: -0.1700
Data Index: 3356564 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.6695. Min Act: -0.1700
Data Index: 7821279 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.6695. Min Act: -0.1700
Data Index: 7683253 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8570. Min Range: -5.8570
Max Act: 5.6383. Min Act: -0.1700
Data Index: 3599870 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19