Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1547 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7791. Min Range: -4.7791
Max Act: 4.7791. Min Act: -0.1700
Data Index: 4529352 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7791. Min Range: -4.7791
Max Act: 4.7166. Min Act: -0.1700
Data Index: 1679618 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7791. Min Range: -4.7791
Max Act: 4.6541. Min Act: -0.1700
Data Index: 1827956 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7791. Min Range: -4.7791
Max Act: 4.5916. Min Act: -0.1700
Data Index: 934129 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7791. Min Range: -4.7791
Max Act: 4.5916. Min Act: -0.1700
Data Index: 2357411 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7791. Min Range: -4.7791
Max Act: 4.5291. Min Act: -0.1700
Data Index: 4109568 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7791. Min Range: -4.7791
Max Act: 4.4353. Min Act: -0.1700
Data Index: 6237708 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7791. Min Range: -4.7791
Max Act: 4.4353. Min Act: -0.1700
Data Index: 2093575 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7791. Min Range: -4.7791
Max Act: 4.4353. Min Act: -0.1700
Data Index: 5959951 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7791. Min Range: -4.7791
Max Act: 4.4040. Min Act: -0.1700
Data Index: 7324131 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7791. Min Range: -4.7791
Max Act: 4.4040. Min Act: -0.1700
Data Index: 2504296 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7791. Min Range: -4.7791
Max Act: 4.4040. Min Act: -0.1700
Data Index: 5171662 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7791. Min Range: -4.7791
Max Act: 4.3728. Min Act: -0.1700
Data Index: 408576 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7791. Min Range: -4.7791
Max Act: 4.4040. Min Act: -0.1700
Data Index: 6092309 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7791. Min Range: -4.7791
Max Act: 4.3728. Min Act: -0.1700
Data Index: 805405 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7791. Min Range: -4.7791
Max Act: 4.3728. Min Act: -0.1700
Data Index: 3623202 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7791. Min Range: -4.7791
Max Act: 4.3415. Min Act: -0.1700
Data Index: 6611626 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7791. Min Range: -4.7791
Max Act: 4.3415. Min Act: -0.1700
Data Index: 6056918 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7791. Min Range: -4.7791
Max Act: 4.3415. Min Act: -0.1700
Data Index: 4647814 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7791. Min Range: -4.7791
Max Act: 4.3415. Min Act: -0.1700
Data Index: 597319 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19