Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4622 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5836. Min Range: -3.5836
Max Act: 3.5836. Min Act: -0.1700
Data Index: 1249967 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5836. Min Range: -3.5836
Max Act: 3.5680. Min Act: -0.1700
Data Index: 5719051 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5836. Min Range: -3.5836
Max Act: 3.4897. Min Act: -0.1700
Data Index: 6457985 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5836. Min Range: -3.5836
Max Act: 3.4740. Min Act: -0.1700
Data Index: 1378817 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5836. Min Range: -3.5836
Max Act: 3.4583. Min Act: -0.1700
Data Index: 6771647 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5836. Min Range: -3.5836
Max Act: 3.4427. Min Act: -0.1700
Data Index: 6139135 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5836. Min Range: -3.5836
Max Act: 3.4427. Min Act: -0.1700
Data Index: 5105747 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5836. Min Range: -3.5836
Max Act: 3.3956. Min Act: -0.1700
Data Index: 411922 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5836. Min Range: -3.5836
Max Act: 3.3956. Min Act: -0.1700
Data Index: 2868267 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5836. Min Range: -3.5836
Max Act: 3.3643. Min Act: -0.1700
Data Index: 3122271 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5836. Min Range: -3.5836
Max Act: 3.3486. Min Act: -0.1700
Data Index: 477945 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5836. Min Range: -3.5836
Max Act: 3.3172. Min Act: -0.1700
Data Index: 4005 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5836. Min Range: -3.5836
Max Act: 3.2858. Min Act: -0.1700
Data Index: 7564489 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5836. Min Range: -3.5836
Max Act: 3.2858. Min Act: -0.1700
Data Index: 2792349 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5836. Min Range: -3.5836
Max Act: 3.2701. Min Act: -0.1700
Data Index: 5105746 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5836. Min Range: -3.5836
Max Act: 3.2701. Min Act: -0.1700
Data Index: 7640639 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5836. Min Range: -3.5836
Max Act: 3.2544. Min Act: -0.1700
Data Index: 803780 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5836. Min Range: -3.5836
Max Act: 3.2544. Min Act: -0.1700
Data Index: 1456030 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5836. Min Range: -3.5836
Max Act: 3.2544. Min Act: -0.1700
Data Index: 6774511 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5836. Min Range: -3.5836
Max Act: 3.2544. Min Act: -0.1700
Data Index: 4020138 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19