Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 696 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.3070. Min Range: -1.3070
Max Act: 1.3070. Min Act: -0.1700
Data Index: 5269575 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3070. Min Range: -1.3070
Max Act: 1.2806. Min Act: -0.1700
Data Index: 5637977 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3070. Min Range: -1.3070
Max Act: 1.2277. Min Act: -0.1700
Data Index: 2050265 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3070. Min Range: -1.3070
Max Act: 1.2277. Min Act: -0.1700
Data Index: 7534605 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3070. Min Range: -1.3070
Max Act: 1.1924. Min Act: -0.1700
Data Index: 1666318 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3070. Min Range: -1.3070
Max Act: 1.1748. Min Act: -0.1700
Data Index: 486291 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3070. Min Range: -1.3070
Max Act: 1.1748. Min Act: -0.1700
Data Index: 6377906 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3070. Min Range: -1.3070
Max Act: 1.1748. Min Act: -0.1700
Data Index: 6603885 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3070. Min Range: -1.3070
Max Act: 1.1573. Min Act: -0.1700
Data Index: 4455459 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3070. Min Range: -1.3070
Max Act: 1.1397. Min Act: -0.1700
Data Index: 8297107 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3070. Min Range: -1.3070
Max Act: 1.1573. Min Act: -0.1700
Data Index: 8377079 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3070. Min Range: -1.3070
Max Act: 1.1221. Min Act: -0.1700
Data Index: 832275 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3070. Min Range: -1.3070
Max Act: 1.1134. Min Act: -0.1700
Data Index: 5502585 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3070. Min Range: -1.3070
Max Act: 1.1221. Min Act: -0.1700
Data Index: 3838803 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3070. Min Range: -1.3070
Max Act: 1.1046. Min Act: -0.1700
Data Index: 1490888 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3070. Min Range: -1.3070
Max Act: 1.1134. Min Act: -0.1700
Data Index: 398424 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3070. Min Range: -1.3070
Max Act: 1.1134. Min Act: -0.1700
Data Index: 1776127 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3070. Min Range: -1.3070
Max Act: 1.1046. Min Act: -0.1700
Data Index: 4692015 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3070. Min Range: -1.3070
Max Act: 1.0958. Min Act: -0.1700
Data Index: 7328679 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3070. Min Range: -1.3070
Max Act: 1.1046. Min Act: -0.1700
Data Index: 4482689 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19