Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4435 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9218. Min Range: -2.9218
Max Act: 2.9218. Min Act: -0.1700
Data Index: 3956964 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9218. Min Range: -2.9218
Max Act: 2.9060. Min Act: -0.1700
Data Index: 6580783 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9218. Min Range: -2.9218
Max Act: 2.9218. Min Act: -0.1700
Data Index: 7341227 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9218. Min Range: -2.9218
Max Act: 2.9060. Min Act: -0.1700
Data Index: 8486784 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9218. Min Range: -2.9218
Max Act: 2.9060. Min Act: -0.1700
Data Index: 8008022 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9218. Min Range: -2.9218
Max Act: 2.8901. Min Act: -0.1700
Data Index: 2742352 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9218. Min Range: -2.9218
Max Act: 2.9060. Min Act: -0.1700
Data Index: 1208115 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9218. Min Range: -2.9218
Max Act: 2.8901. Min Act: -0.1700
Data Index: 4187879 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9218. Min Range: -2.9218
Max Act: 2.8901. Min Act: -0.1700
Data Index: 4768232 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9218. Min Range: -2.9218
Max Act: 2.8584. Min Act: -0.1700
Data Index: 8792665 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9218. Min Range: -2.9218
Max Act: 2.8425. Min Act: -0.1700
Data Index: 5057251 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9218. Min Range: -2.9218
Max Act: 2.8584. Min Act: -0.1700
Data Index: 1403933 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9218. Min Range: -2.9218
Max Act: 2.8584. Min Act: -0.1700
Data Index: 8346425 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9218. Min Range: -2.9218
Max Act: 2.8584. Min Act: -0.1700
Data Index: 1802343 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9218. Min Range: -2.9218
Max Act: 2.8425. Min Act: -0.1700
Data Index: 6580766 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9218. Min Range: -2.9218
Max Act: 2.8266. Min Act: -0.1700
Data Index: 8263505 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9218. Min Range: -2.9218
Max Act: 2.8266. Min Act: -0.1700
Data Index: 7041911 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9218. Min Range: -2.9218
Max Act: 2.8266. Min Act: -0.1700
Data Index: 1106531 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9218. Min Range: -2.9218
Max Act: 2.8266. Min Act: -0.1700
Data Index: 2699947 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9218. Min Range: -2.9218
Max Act: 2.8107. Min Act: -0.1700
Data Index: 6008525 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19