Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1579 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9043. Min Range: -3.9043
Max Act: 3.9043. Min Act: -0.1700
Data Index: 1395025 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9043. Min Range: -3.9043
Max Act: 3.9043. Min Act: -0.1700
Data Index: 7947201 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9043. Min Range: -3.9043
Max Act: 3.8730. Min Act: -0.1700
Data Index: 7885835 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9043. Min Range: -3.9043
Max Act: 3.8730. Min Act: -0.1700
Data Index: 6889390 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9043. Min Range: -3.9043
Max Act: 3.8574. Min Act: -0.1700
Data Index: 1616194 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9043. Min Range: -3.9043
Max Act: 3.8574. Min Act: -0.1700
Data Index: 8014678 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9043. Min Range: -3.9043
Max Act: 3.8261. Min Act: -0.1700
Data Index: 1055440 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9043. Min Range: -3.9043
Max Act: 3.8105. Min Act: -0.1700
Data Index: 5793091 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9043. Min Range: -3.9043
Max Act: 3.7636. Min Act: -0.1700
Data Index: 8557702 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9043. Min Range: -3.9043
Max Act: 3.7636. Min Act: -0.1700
Data Index: 3555004 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9043. Min Range: -3.9043
Max Act: 3.7949. Min Act: -0.1700
Data Index: 2136343 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9043. Min Range: -3.9043
Max Act: 3.7636. Min Act: -0.1700
Data Index: 251977 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9043. Min Range: -3.9043
Max Act: 3.7636. Min Act: -0.1700
Data Index: 1337370 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9043. Min Range: -3.9043
Max Act: 3.7480. Min Act: -0.1700
Data Index: 4993666 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9043. Min Range: -3.9043
Max Act: 3.7323. Min Act: -0.1700
Data Index: 2080794 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9043. Min Range: -3.9043
Max Act: 3.7323. Min Act: -0.1700
Data Index: 6444592 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9043. Min Range: -3.9043
Max Act: 3.7010. Min Act: -0.1700
Data Index: 3480834 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9043. Min Range: -3.9043
Max Act: 3.7010. Min Act: -0.1700
Data Index: 5925231 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9043. Min Range: -3.9043
Max Act: 3.7010. Min Act: -0.1700
Data Index: 1056605 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9043. Min Range: -3.9043
Max Act: 3.6854. Min Act: -0.1700
Data Index: 5387809 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19