Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2026 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7822. Min Range: -9.7822
Max Act: 9.7822. Min Act: -0.1700
Data Index: 4810354 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7822. Min Range: -9.7822
Max Act: 9.5947. Min Act: -0.1700
Data Index: 3558159 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7822. Min Range: -9.7822
Max Act: 9.2197. Min Act: -0.1700
Data Index: 8239282 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7822. Min Range: -9.7822
Max Act: 9.1572. Min Act: -0.1700
Data Index: 5058480 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7822. Min Range: -9.7822
Max Act: 9.1572. Min Act: -0.1700
Data Index: 6199470 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7822. Min Range: -9.7822
Max Act: 9.1572. Min Act: -0.1700
Data Index: 6282510 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7822. Min Range: -9.7822
Max Act: 9.1572. Min Act: -0.1700
Data Index: 6758981 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7822. Min Range: -9.7822
Max Act: 9.0947. Min Act: -0.1700
Data Index: 6955317 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7822. Min Range: -9.7822
Max Act: 9.0322. Min Act: -0.1700
Data Index: 4711882 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7822. Min Range: -9.7822
Max Act: 9.0947. Min Act: -0.1700
Data Index: 2995419 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7822. Min Range: -9.7822
Max Act: 9.0322. Min Act: -0.1700
Data Index: 601633 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7822. Min Range: -9.7822
Max Act: 8.9697. Min Act: -0.1700
Data Index: 3512369 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7822. Min Range: -9.7822
Max Act: 8.9072. Min Act: -0.1700
Data Index: 8065947 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7822. Min Range: -9.7822
Max Act: 8.8447. Min Act: -0.1700
Data Index: 7048070 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7822. Min Range: -9.7822
Max Act: 8.7822. Min Act: -0.1700
Data Index: 5199248 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7822. Min Range: -9.7822
Max Act: 8.7822. Min Act: -0.1700
Data Index: 5979042 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7822. Min Range: -9.7822
Max Act: 8.7822. Min Act: -0.1700
Data Index: 7704807 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7822. Min Range: -9.7822
Max Act: 8.7197. Min Act: -0.1700
Data Index: 4871603 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7822. Min Range: -9.7822
Max Act: 8.7197. Min Act: -0.1700
Data Index: 1725600 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7822. Min Range: -9.7822
Max Act: 8.7822. Min Act: -0.1700
Data Index: 7215154 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19