Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 45 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2402. Min Range: -6.2402
Max Act: 6.2402. Min Act: -0.1700
Data Index: 1854162 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2402. Min Range: -6.2402
Max Act: 6.2090. Min Act: -0.1700
Data Index: 6813683 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2402. Min Range: -6.2402
Max Act: 6.2090. Min Act: -0.1700
Data Index: 1905495 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2402. Min Range: -6.2402
Max Act: 6.1777. Min Act: -0.1700
Data Index: 6236050 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2402. Min Range: -6.2402
Max Act: 6.1465. Min Act: -0.1700
Data Index: 560882 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2402. Min Range: -6.2402
Max Act: 6.1465. Min Act: -0.1700
Data Index: 3395417 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2402. Min Range: -6.2402
Max Act: 6.0527. Min Act: -0.1700
Data Index: 8823361 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2402. Min Range: -6.2402
Max Act: 6.0527. Min Act: -0.1700
Data Index: 6300156 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2402. Min Range: -6.2402
Max Act: 6.0527. Min Act: -0.1700
Data Index: 3148539 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2402. Min Range: -6.2402
Max Act: 6.0215. Min Act: -0.1700
Data Index: 1485509 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.9590. Min Act: -0.1700
Data Index: 5667748 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.9277. Min Act: -0.1700
Data Index: 5966317 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.9277. Min Act: -0.1700
Data Index: 6777908 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.9277. Min Act: -0.1700
Data Index: 1081064 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.9277. Min Act: -0.1700
Data Index: 294734 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.8965. Min Act: -0.1700
Data Index: 2970133 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.8965. Min Act: -0.1700
Data Index: 5978454 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.8652. Min Act: -0.1700
Data Index: 6399513 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.8652. Min Act: -0.1700
Data Index: 5336756 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.8340. Min Act: -0.1700
Data Index: 1091875 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19