Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2608 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9123. Min Range: -6.9123
Max Act: 6.9123. Min Act: -0.1700
Data Index: 5174709 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9123. Min Range: -6.9123
Max Act: 6.7560. Min Act: -0.1700
Data Index: 793945 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9123. Min Range: -6.9123
Max Act: 6.6623. Min Act: -0.1700
Data Index: 1106074 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9123. Min Range: -6.9123
Max Act: 6.5998. Min Act: -0.1700
Data Index: 4635660 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9123. Min Range: -6.9123
Max Act: 6.5685. Min Act: -0.1700
Data Index: 3583217 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9123. Min Range: -6.9123
Max Act: 6.5373. Min Act: -0.1700
Data Index: 2951432 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9123. Min Range: -6.9123
Max Act: 6.4748. Min Act: -0.1700
Data Index: 6703597 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9123. Min Range: -6.9123
Max Act: 6.4748. Min Act: -0.1700
Data Index: 7935203 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9123. Min Range: -6.9123
Max Act: 6.4435. Min Act: -0.1700
Data Index: 2228207 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9123. Min Range: -6.9123
Max Act: 6.5060. Min Act: -0.1700
Data Index: 3644057 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9123. Min Range: -6.9123
Max Act: 6.4748. Min Act: -0.1700
Data Index: 558600 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9123. Min Range: -6.9123
Max Act: 6.4435. Min Act: -0.1700
Data Index: 5734902 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9123. Min Range: -6.9123
Max Act: 6.4748. Min Act: -0.1700
Data Index: 6449618 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9123. Min Range: -6.9123
Max Act: 6.3810. Min Act: -0.1700
Data Index: 7686532 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9123. Min Range: -6.9123
Max Act: 6.3810. Min Act: -0.1700
Data Index: 6615188 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9123. Min Range: -6.9123
Max Act: 6.3498. Min Act: -0.1700
Data Index: 5494141 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9123. Min Range: -6.9123
Max Act: 6.3185. Min Act: -0.1700
Data Index: 998306 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9123. Min Range: -6.9123
Max Act: 6.3185. Min Act: -0.1700
Data Index: 1006890 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9123. Min Range: -6.9123
Max Act: 6.3185. Min Act: -0.1700
Data Index: 4614557 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9123. Min Range: -6.9123
Max Act: 6.2873. Min Act: -0.1700
Data Index: 1821861 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19