Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3172 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3774. Min Range: -4.3774
Max Act: 4.3774. Min Act: -0.1700
Data Index: 2125737 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3774. Min Range: -4.3774
Max Act: 4.2212. Min Act: -0.1700
Data Index: 4117337 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3774. Min Range: -4.3774
Max Act: 4.2212. Min Act: -0.1700
Data Index: 7230493 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3774. Min Range: -4.3774
Max Act: 4.2212. Min Act: -0.1700
Data Index: 2968229 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3774. Min Range: -4.3774
Max Act: 4.1899. Min Act: -0.1700
Data Index: 4035118 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3774. Min Range: -4.3774
Max Act: 4.1899. Min Act: -0.1700
Data Index: 7260523 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3774. Min Range: -4.3774
Max Act: 4.1899. Min Act: -0.1700
Data Index: 2806368 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3774. Min Range: -4.3774
Max Act: 4.1899. Min Act: -0.1700
Data Index: 2729228 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3774. Min Range: -4.3774
Max Act: 4.1587. Min Act: -0.1700
Data Index: 2951584 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3774. Min Range: -4.3774
Max Act: 4.1587. Min Act: -0.1700
Data Index: 2012177 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3774. Min Range: -4.3774
Max Act: 4.1587. Min Act: -0.1700
Data Index: 4251941 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3774. Min Range: -4.3774
Max Act: 4.1587. Min Act: -0.1700
Data Index: 2038791 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3774. Min Range: -4.3774
Max Act: 4.1587. Min Act: -0.1700
Data Index: 251023 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3774. Min Range: -4.3774
Max Act: 4.1587. Min Act: -0.1700
Data Index: 6362154 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3774. Min Range: -4.3774
Max Act: 4.1587. Min Act: -0.1700
Data Index: 6435183 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3774. Min Range: -4.3774
Max Act: 4.1587. Min Act: -0.1700
Data Index: 2395642 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3774. Min Range: -4.3774
Max Act: 4.1587. Min Act: -0.1700
Data Index: 1833991 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3774. Min Range: -4.3774
Max Act: 4.1587. Min Act: -0.1700
Data Index: 2499597 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3774. Min Range: -4.3774
Max Act: 4.1587. Min Act: -0.1700
Data Index: 3897762 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3774. Min Range: -4.3774
Max Act: 4.1587. Min Act: -0.1700
Data Index: 1935180 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19