Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5638 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3090. Min Range: -7.3090
Max Act: 7.2777. Min Act: -0.1700
Data Index: 5089984 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3090. Min Range: -7.3090
Max Act: 7.2777. Min Act: -0.1700
Data Index: 8422356 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3090. Min Range: -7.3090
Max Act: 7.3090. Min Act: -0.1700
Data Index: 5595548 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3090. Min Range: -7.3090
Max Act: 7.2152. Min Act: -0.1700
Data Index: 7424310 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3090. Min Range: -7.3090
Max Act: 7.2465. Min Act: -0.1700
Data Index: 1104423 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3090. Min Range: -7.3090
Max Act: 7.1840. Min Act: -0.1700
Data Index: 2314099 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3090. Min Range: -7.3090
Max Act: 7.0902. Min Act: -0.1700
Data Index: 3740267 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3090. Min Range: -7.3090
Max Act: 7.0590. Min Act: -0.1700
Data Index: 7249111 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3090. Min Range: -7.3090
Max Act: 7.0277. Min Act: -0.1700
Data Index: 1062574 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3090. Min Range: -7.3090
Max Act: 6.9965. Min Act: -0.1700
Data Index: 322048 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3090. Min Range: -7.3090
Max Act: 6.9652. Min Act: -0.1700
Data Index: 2432044 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3090. Min Range: -7.3090
Max Act: 6.9340. Min Act: -0.1700
Data Index: 5486946 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3090. Min Range: -7.3090
Max Act: 6.9340. Min Act: -0.1700
Data Index: 1966430 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3090. Min Range: -7.3090
Max Act: 6.8715. Min Act: -0.1700
Data Index: 8164595 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3090. Min Range: -7.3090
Max Act: 6.9027. Min Act: -0.1700
Data Index: 642032 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3090. Min Range: -7.3090
Max Act: 6.9340. Min Act: -0.1700
Data Index: 2429141 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3090. Min Range: -7.3090
Max Act: 6.8715. Min Act: -0.1700
Data Index: 5161180 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3090. Min Range: -7.3090
Max Act: 6.8715. Min Act: -0.1700
Data Index: 1112200 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3090. Min Range: -7.3090
Max Act: 6.8402. Min Act: -0.1700
Data Index: 3153237 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3090. Min Range: -7.3090
Max Act: 6.8402. Min Act: -0.1700
Data Index: 3221898 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19