Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4902 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0785. Min Range: -5.0785
Max Act: 5.0785. Min Act: -0.1700
Data Index: 1930831 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0785. Min Range: -5.0785
Max Act: 5.0160. Min Act: -0.1700
Data Index: 5318153 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0785. Min Range: -5.0785
Max Act: 4.9847. Min Act: -0.1700
Data Index: 1426577 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0785. Min Range: -5.0785
Max Act: 4.9847. Min Act: -0.1700
Data Index: 1810067 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0785. Min Range: -5.0785
Max Act: 4.9847. Min Act: -0.1700
Data Index: 5519464 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0785. Min Range: -5.0785
Max Act: 4.9847. Min Act: -0.1700
Data Index: 8802964 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0785. Min Range: -5.0785
Max Act: 4.9535. Min Act: -0.1700
Data Index: 4883594 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0785. Min Range: -5.0785
Max Act: 4.9535. Min Act: -0.1700
Data Index: 384879 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0785. Min Range: -5.0785
Max Act: 4.9222. Min Act: -0.1700
Data Index: 3204115 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0785. Min Range: -5.0785
Max Act: 4.9222. Min Act: -0.1700
Data Index: 961775 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0785. Min Range: -5.0785
Max Act: 4.9222. Min Act: -0.1700
Data Index: 7857897 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0785. Min Range: -5.0785
Max Act: 4.9222. Min Act: -0.1700
Data Index: 6448528 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0785. Min Range: -5.0785
Max Act: 4.8910. Min Act: -0.1700
Data Index: 1092747 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0785. Min Range: -5.0785
Max Act: 4.8910. Min Act: -0.1700
Data Index: 8629376 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0785. Min Range: -5.0785
Max Act: 4.8910. Min Act: -0.1700
Data Index: 6402480 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0785. Min Range: -5.0785
Max Act: 4.8910. Min Act: -0.1700
Data Index: 7718431 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0785. Min Range: -5.0785
Max Act: 4.8910. Min Act: -0.1700
Data Index: 8515286 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0785. Min Range: -5.0785
Max Act: 4.8597. Min Act: -0.1700
Data Index: 4577758 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0785. Min Range: -5.0785
Max Act: 4.8597. Min Act: -0.1700
Data Index: 7857049 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0785. Min Range: -5.0785
Max Act: 4.8285. Min Act: -0.1700
Data Index: 6766301 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19