Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2774 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0159. Min Range: -7.0159
Max Act: 7.0159. Min Act: -0.1700
Data Index: 21936 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.9221. Min Act: -0.1700
Data Index: 4797092 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.9534. Min Act: -0.1700
Data Index: 2232001 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.8284. Min Act: -0.1700
Data Index: 6866296 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.8284. Min Act: -0.1700
Data Index: 7393460 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.7971. Min Act: -0.1700
Data Index: 6147503 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.7971. Min Act: -0.1700
Data Index: 7556894 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.7971. Min Act: -0.1700
Data Index: 1673953 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.7971. Min Act: -0.1700
Data Index: 4372728 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.7659. Min Act: -0.1700
Data Index: 3678661 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.7659. Min Act: -0.1700
Data Index: 7730590 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.7659. Min Act: -0.1700
Data Index: 3532269 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.7659. Min Act: -0.1700
Data Index: 1084861 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.7346. Min Act: -0.1700
Data Index: 6720898 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.7346. Min Act: -0.1700
Data Index: 4098741 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.7346. Min Act: -0.1700
Data Index: 633561 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.7346. Min Act: -0.1700
Data Index: 7237518 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.7034. Min Act: -0.1700
Data Index: 4672325 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.7034. Min Act: -0.1700
Data Index: 3615656 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0159. Min Range: -7.0159
Max Act: 6.7034. Min Act: -0.1700
Data Index: 4689794 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19