Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1612 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.3990. Min Act: -0.1700
Data Index: 2845278 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.4304. Min Act: -0.1700
Data Index: 586128 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.4304. Min Act: -0.1700
Data Index: 5101005 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.4304. Min Act: -0.1700
Data Index: 789292 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.3990. Min Act: -0.1700
Data Index: 2527731 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.3990. Min Act: -0.1700
Data Index: 8370969 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.3990. Min Act: -0.1700
Data Index: 815301 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.3990. Min Act: -0.1700
Data Index: 7212742 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.3990. Min Act: -0.1700
Data Index: 7101673 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.3990. Min Act: -0.1700
Data Index: 5866048 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.3990. Min Act: -0.1700
Data Index: 4855233 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.3990. Min Act: -0.1700
Data Index: 3993000 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.3990. Min Act: -0.1700
Data Index: 62893 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.3990. Min Act: -0.1700
Data Index: 3827291 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.3677. Min Act: -0.1700
Data Index: 3561742 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.3990. Min Act: -0.1700
Data Index: 3396410 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.3677. Min Act: -0.1700
Data Index: 3340256 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.3677. Min Act: -0.1700
Data Index: 2462793 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.3677. Min Act: -0.1700
Data Index: 1841865 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4304. Min Range: -3.4304
Max Act: 3.3677. Min Act: -0.1700
Data Index: 2035671 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19