Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4638 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2088. Min Range: -4.2088
Max Act: 4.2088. Min Act: -0.1700
Data Index: 729574 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2088. Min Range: -4.2088
Max Act: 4.1150. Min Act: -0.1700
Data Index: 2370988 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2088. Min Range: -4.2088
Max Act: 4.1150. Min Act: -0.1700
Data Index: 6094279 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2088. Min Range: -4.2088
Max Act: 4.0838. Min Act: -0.1700
Data Index: 5408338 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2088. Min Range: -4.2088
Max Act: 4.0525. Min Act: -0.1700
Data Index: 3271323 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2088. Min Range: -4.2088
Max Act: 4.0213. Min Act: -0.1700
Data Index: 4495429 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2088. Min Range: -4.2088
Max Act: 3.9588. Min Act: -0.1700
Data Index: 4440021 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2088. Min Range: -4.2088
Max Act: 3.9275. Min Act: -0.1700
Data Index: 5320864 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2088. Min Range: -4.2088
Max Act: 3.9275. Min Act: -0.1700
Data Index: 6264080 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2088. Min Range: -4.2088
Max Act: 3.8962. Min Act: -0.1700
Data Index: 3124961 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2088. Min Range: -4.2088
Max Act: 3.9275. Min Act: -0.1700
Data Index: 3080370 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2088. Min Range: -4.2088
Max Act: 3.9275. Min Act: -0.1700
Data Index: 5112802 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2088. Min Range: -4.2088
Max Act: 3.8650. Min Act: -0.1700
Data Index: 4193951 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2088. Min Range: -4.2088
Max Act: 3.8650. Min Act: -0.1700
Data Index: 1760764 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2088. Min Range: -4.2088
Max Act: 3.8650. Min Act: -0.1700
Data Index: 2129278 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2088. Min Range: -4.2088
Max Act: 3.8650. Min Act: -0.1700
Data Index: 5190965 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2088. Min Range: -4.2088
Max Act: 3.8650. Min Act: -0.1700
Data Index: 6725974 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2088. Min Range: -4.2088
Max Act: 3.8024. Min Act: -0.1700
Data Index: 2164716 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2088. Min Range: -4.2088
Max Act: 3.8650. Min Act: -0.1700
Data Index: 5338415 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2088. Min Range: -4.2088
Max Act: 3.8337. Min Act: -0.1700
Data Index: 2708994 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19