Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 552 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3345. Min Range: -4.3345
Max Act: 4.3345. Min Act: -0.1700
Data Index: 6723175 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3345. Min Range: -4.3345
Max Act: 4.2095. Min Act: -0.1700
Data Index: 1534394 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3345. Min Range: -4.3345
Max Act: 4.1782. Min Act: -0.1700
Data Index: 5418639 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3345. Min Range: -4.3345
Max Act: 4.1157. Min Act: -0.1700
Data Index: 7472791 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3345. Min Range: -4.3345
Max Act: 4.0845. Min Act: -0.1698
Data Index: 1773998 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3345. Min Range: -4.3345
Max Act: 4.1157. Min Act: -0.1699
Data Index: 6190277 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3345. Min Range: -4.3345
Max Act: 4.0532. Min Act: -0.1700
Data Index: 4594275 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3345. Min Range: -4.3345
Max Act: 4.0845. Min Act: -0.1700
Data Index: 4361037 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3345. Min Range: -4.3345
Max Act: 4.0845. Min Act: -0.1699
Data Index: 5812856 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3345. Min Range: -4.3345
Max Act: 4.0845. Min Act: -0.1700
Data Index: 4726243 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3345. Min Range: -4.3345
Max Act: 4.0532. Min Act: -0.1700
Data Index: 5982362 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3345. Min Range: -4.3345
Max Act: 4.0532. Min Act: -0.1700
Data Index: 3614407 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3345. Min Range: -4.3345
Max Act: 4.0532. Min Act: -0.1700
Data Index: 4330107 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3345. Min Range: -4.3345
Max Act: 4.0532. Min Act: -0.1700
Data Index: 223293 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3345. Min Range: -4.3345
Max Act: 4.0220. Min Act: -0.1700
Data Index: 2256705 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3345. Min Range: -4.3345
Max Act: 4.0220. Min Act: -0.1700
Data Index: 8728099 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3345. Min Range: -4.3345
Max Act: 4.0220. Min Act: -0.1700
Data Index: 4593509 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3345. Min Range: -4.3345
Max Act: 3.9907. Min Act: -0.1700
Data Index: 1155036 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3345. Min Range: -4.3345
Max Act: 3.9907. Min Act: -0.1699
Data Index: 3558317 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3345. Min Range: -4.3345
Max Act: 3.9594. Min Act: -0.1700
Data Index: 1524207 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19