Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2430 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4024. Min Range: -5.4024
Max Act: 5.4024. Min Act: -0.1700
Data Index: 569902 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4024. Min Range: -5.4024
Max Act: 5.4024. Min Act: -0.1700
Data Index: 6919002 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4024. Min Range: -5.4024
Max Act: 5.4024. Min Act: -0.1698
Data Index: 1831170 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4024. Min Range: -5.4024
Max Act: 5.3711. Min Act: -0.1699
Data Index: 8515906 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4024. Min Range: -5.4024
Max Act: 5.3711. Min Act: -0.1698
Data Index: 689137 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4024. Min Range: -5.4024
Max Act: 5.3399. Min Act: -0.1700
Data Index: 3663670 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4024. Min Range: -5.4024
Max Act: 5.3086. Min Act: -0.1700
Data Index: 6133524 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4024. Min Range: -5.4024
Max Act: 5.3086. Min Act: -0.1700
Data Index: 7240630 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4024. Min Range: -5.4024
Max Act: 5.3399. Min Act: -0.1700
Data Index: 2871851 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4024. Min Range: -5.4024
Max Act: 5.3086. Min Act: -0.1699
Data Index: 2178908 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4024. Min Range: -5.4024
Max Act: 5.3086. Min Act: -0.1700
Data Index: 978499 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4024. Min Range: -5.4024
Max Act: 5.3086. Min Act: -0.1700
Data Index: 4288550 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4024. Min Range: -5.4024
Max Act: 5.3399. Min Act: -0.1700
Data Index: 2039533 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4024. Min Range: -5.4024
Max Act: 5.3086. Min Act: -0.1690
Data Index: 1714165 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4024. Min Range: -5.4024
Max Act: 5.3086. Min Act: -0.1700
Data Index: 4855256 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4024. Min Range: -5.4024
Max Act: 5.3086. Min Act: -0.1699
Data Index: 4796065 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4024. Min Range: -5.4024
Max Act: 5.3086. Min Act: -0.1700
Data Index: 239970 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4024. Min Range: -5.4024
Max Act: 5.3086. Min Act: -0.1690
Data Index: 3604970 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4024. Min Range: -5.4024
Max Act: 5.2774. Min Act: -0.1700
Data Index: 692212 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4024. Min Range: -5.4024
Max Act: 5.2774. Min Act: -0.1700
Data Index: 3577534 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19