Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1727 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2639. Min Range: -1.2639
Max Act: 1.2639. Min Act: -0.1700
Data Index: 3475319 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2639. Min Range: -1.2639
Max Act: 1.2463. Min Act: -0.1673
Data Index: 5364548 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2639. Min Range: -1.2639
Max Act: 1.2375. Min Act: -0.1686
Data Index: 4417137 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2639. Min Range: -1.2639
Max Act: 1.2463. Min Act: -0.1631
Data Index: 2738958 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2639. Min Range: -1.2639
Max Act: 1.2286. Min Act: -0.1681
Data Index: 2807169 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2639. Min Range: -1.2639
Max Act: 1.2198. Min Act: -0.1695
Data Index: 3716150 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2639. Min Range: -1.2639
Max Act: 1.2286. Min Act: -0.1700
Data Index: 2163932 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2639. Min Range: -1.2639
Max Act: 1.2110. Min Act: -0.1700
Data Index: 6907127 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2639. Min Range: -1.2639
Max Act: 1.2198. Min Act: -0.1700
Data Index: 3837443 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2639. Min Range: -1.2639
Max Act: 1.2110. Min Act: -0.1700
Data Index: 6252508 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2639. Min Range: -1.2639
Max Act: 1.2110. Min Act: -0.1700
Data Index: 7476474 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2639. Min Range: -1.2639
Max Act: 1.2022. Min Act: -0.1700
Data Index: 8187031 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2639. Min Range: -1.2639
Max Act: 1.2022. Min Act: -0.1700
Data Index: 6366524 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2639. Min Range: -1.2639
Max Act: 1.2022. Min Act: -0.1700
Data Index: 5668542 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2639. Min Range: -1.2639
Max Act: 1.1934. Min Act: -0.1700
Data Index: 2304342 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2639. Min Range: -1.2639
Max Act: 1.1846. Min Act: -0.1700
Data Index: 6898829 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2639. Min Range: -1.2639
Max Act: 1.1934. Min Act: -0.1700
Data Index: 5445529 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2639. Min Range: -1.2639
Max Act: 1.1934. Min Act: -0.1700
Data Index: 7093294 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2639. Min Range: -1.2639
Max Act: 1.1846. Min Act: -0.1700
Data Index: 1847600 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2639. Min Range: -1.2639
Max Act: 1.1846. Min Act: -0.1699
Data Index: 7406966 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19