Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 789 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3573. Min Range: -5.3573
Max Act: 5.3573. Min Act: -0.1700
Data Index: 7311365 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3573. Min Range: -5.3573
Max Act: 5.3261. Min Act: -0.1700
Data Index: 6705493 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3573. Min Range: -5.3573
Max Act: 5.3261. Min Act: -0.1700
Data Index: 1749529 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3573. Min Range: -5.3573
Max Act: 5.2948. Min Act: -0.1700
Data Index: 5215718 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3573. Min Range: -5.3573
Max Act: 5.2636. Min Act: -0.1700
Data Index: 233627 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3573. Min Range: -5.3573
Max Act: 5.2948. Min Act: -0.1700
Data Index: 8739261 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3573. Min Range: -5.3573
Max Act: 5.2323. Min Act: -0.1700
Data Index: 2885741 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3573. Min Range: -5.3573
Max Act: 5.2323. Min Act: -0.1700
Data Index: 4304230 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3573. Min Range: -5.3573
Max Act: 5.2323. Min Act: -0.1700
Data Index: 1015912 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3573. Min Range: -5.3573
Max Act: 5.2323. Min Act: -0.1700
Data Index: 4447803 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3573. Min Range: -5.3573
Max Act: 5.2636. Min Act: -0.1700
Data Index: 6095095 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3573. Min Range: -5.3573
Max Act: 5.2011. Min Act: -0.1700
Data Index: 8245985 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3573. Min Range: -5.3573
Max Act: 5.2323. Min Act: -0.1700
Data Index: 7429766 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3573. Min Range: -5.3573
Max Act: 5.2011. Min Act: -0.1700
Data Index: 4911881 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3573. Min Range: -5.3573
Max Act: 5.1386. Min Act: -0.1700
Data Index: 2810162 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3573. Min Range: -5.3573
Max Act: 5.1698. Min Act: -0.1700
Data Index: 6401582 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3573. Min Range: -5.3573
Max Act: 5.1698. Min Act: -0.1700
Data Index: 1727727 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3573. Min Range: -5.3573
Max Act: 5.1386. Min Act: -0.1700
Data Index: 1659560 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3573. Min Range: -5.3573
Max Act: 5.1073. Min Act: -0.1700
Data Index: 4403394 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3573. Min Range: -5.3573
Max Act: 5.1386. Min Act: -0.1700
Data Index: 2211890 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19