Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5075 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4482. Min Range: -7.4482
Max Act: 7.4482. Min Act: -0.1700
Data Index: 4319178 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4482. Min Range: -7.4482
Max Act: 7.3232. Min Act: -0.1700
Data Index: 3966930 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4482. Min Range: -7.4482
Max Act: 7.2607. Min Act: -0.1700
Data Index: 3400415 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4482. Min Range: -7.4482
Max Act: 7.2607. Min Act: -0.1700
Data Index: 61667 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4482. Min Range: -7.4482
Max Act: 7.1982. Min Act: -0.1700
Data Index: 4660048 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4482. Min Range: -7.4482
Max Act: 7.1357. Min Act: -0.1700
Data Index: 8544966 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4482. Min Range: -7.4482
Max Act: 7.1044. Min Act: -0.1700
Data Index: 5316004 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4482. Min Range: -7.4482
Max Act: 7.1357. Min Act: -0.1700
Data Index: 3685799 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4482. Min Range: -7.4482
Max Act: 7.0107. Min Act: -0.1700
Data Index: 439765 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4482. Min Range: -7.4482
Max Act: 6.9794. Min Act: -0.1700
Data Index: 5007197 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4482. Min Range: -7.4482
Max Act: 6.9169. Min Act: -0.1700
Data Index: 5903499 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4482. Min Range: -7.4482
Max Act: 6.8544. Min Act: -0.1700
Data Index: 8122077 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4482. Min Range: -7.4482
Max Act: 6.8544. Min Act: -0.1700
Data Index: 3593591 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4482. Min Range: -7.4482
Max Act: 6.8544. Min Act: -0.1700
Data Index: 2454140 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4482. Min Range: -7.4482
Max Act: 6.8232. Min Act: -0.1700
Data Index: 5368093 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4482. Min Range: -7.4482
Max Act: 6.7919. Min Act: -0.1700
Data Index: 2652918 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4482. Min Range: -7.4482
Max Act: 6.7919. Min Act: -0.1700
Data Index: 5694975 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4482. Min Range: -7.4482
Max Act: 6.7919. Min Act: -0.1700
Data Index: 4690833 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4482. Min Range: -7.4482
Max Act: 6.7919. Min Act: -0.1700
Data Index: 6990709 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4482. Min Range: -7.4482
Max Act: 6.7919. Min Act: -0.1700
Data Index: 6350189 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19