Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2012 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1960. Min Range: -6.1960
Max Act: 6.1960. Min Act: -0.1700
Data Index: 4582528 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.9460. Min Act: -0.1700
Data Index: 3793608 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.9147. Min Act: -0.1700
Data Index: 6157182 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.8835. Min Act: -0.1700
Data Index: 4112953 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.8835. Min Act: -0.1700
Data Index: 1357192 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.8835. Min Act: -0.1700
Data Index: 7411616 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.8210. Min Act: -0.1700
Data Index: 6156188 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.7897. Min Act: -0.1700
Data Index: 2935113 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.7585. Min Act: -0.1700
Data Index: 5185903 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.7585. Min Act: -0.1700
Data Index: 3534622 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.7272. Min Act: -0.1700
Data Index: 6525798 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.7272. Min Act: -0.1700
Data Index: 6229965 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.6960. Min Act: -0.1700
Data Index: 692721 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.6960. Min Act: -0.1700
Data Index: 6710636 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.6647. Min Act: -0.1700
Data Index: 4431287 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.6647. Min Act: -0.1700
Data Index: 8422362 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.6647. Min Act: -0.1700
Data Index: 4582530 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.6335. Min Act: -0.1700
Data Index: 6058271 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.6335. Min Act: -0.1700
Data Index: 2985507 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.6335. Min Act: -0.1700
Data Index: 6494158 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19