Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3027 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4531. Min Range: -6.4531
Max Act: 6.4531. Min Act: -0.1700
Data Index: 2247876 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4531. Min Range: -6.4531
Max Act: 6.2969. Min Act: -0.1700
Data Index: 3721646 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4531. Min Range: -6.4531
Max Act: 6.2344. Min Act: -0.1700
Data Index: 1896167 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4531. Min Range: -6.4531
Max Act: 6.1406. Min Act: -0.1700
Data Index: 691206 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4531. Min Range: -6.4531
Max Act: 6.0781. Min Act: -0.1700
Data Index: 3985935 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4531. Min Range: -6.4531
Max Act: 6.0781. Min Act: -0.1700
Data Index: 396285 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4531. Min Range: -6.4531
Max Act: 6.0469. Min Act: -0.1700
Data Index: 6209536 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4531. Min Range: -6.4531
Max Act: 5.9844. Min Act: -0.1700
Data Index: 1947517 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4531. Min Range: -6.4531
Max Act: 5.9844. Min Act: -0.1700
Data Index: 3939196 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4531. Min Range: -6.4531
Max Act: 5.9531. Min Act: -0.1700
Data Index: 6736276 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4531. Min Range: -6.4531
Max Act: 5.9531. Min Act: -0.1700
Data Index: 5311436 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4531. Min Range: -6.4531
Max Act: 5.9219. Min Act: -0.1700
Data Index: 7064569 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4531. Min Range: -6.4531
Max Act: 5.9219. Min Act: -0.1700
Data Index: 4397065 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4531. Min Range: -6.4531
Max Act: 5.9531. Min Act: -0.1700
Data Index: 5944782 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4531. Min Range: -6.4531
Max Act: 5.9219. Min Act: -0.1700
Data Index: 5787947 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4531. Min Range: -6.4531
Max Act: 5.9219. Min Act: -0.1700
Data Index: 2402401 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4531. Min Range: -6.4531
Max Act: 5.9219. Min Act: -0.1700
Data Index: 3100585 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4531. Min Range: -6.4531
Max Act: 5.8906. Min Act: -0.1700
Data Index: 5028234 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4531. Min Range: -6.4531
Max Act: 5.8906. Min Act: -0.1700
Data Index: 3224472 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4531. Min Range: -6.4531
Max Act: 5.8906. Min Act: -0.1700
Data Index: 3286718 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19