Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1929 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0785. Min Range: -6.0785
Max Act: 6.0785. Min Act: -0.1700
Data Index: 7765409 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.8598. Min Act: -0.1700
Data Index: 6396956 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.7035. Min Act: -0.1700
Data Index: 4964569 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.7348. Min Act: -0.1700
Data Index: 870153 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.6410. Min Act: -0.1700
Data Index: 5748608 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.6098. Min Act: -0.1700
Data Index: 4950439 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.6098. Min Act: -0.1700
Data Index: 1263003 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.5160. Min Act: -0.1700
Data Index: 4368072 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.5473. Min Act: -0.1700
Data Index: 4590610 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.5473. Min Act: -0.1700
Data Index: 3786283 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.5785. Min Act: -0.1700
Data Index: 2937347 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.5473. Min Act: -0.1700
Data Index: 6068958 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.5473. Min Act: -0.1700
Data Index: 573642 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.5160. Min Act: -0.1700
Data Index: 8223688 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.4848. Min Act: -0.1700
Data Index: 8417959 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.4535. Min Act: -0.1700
Data Index: 1239162 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.4848. Min Act: -0.1700
Data Index: 1728842 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.4535. Min Act: -0.1700
Data Index: 7297297 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.4848. Min Act: -0.1700
Data Index: 3222543 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0785. Min Range: -6.0785
Max Act: 5.4535. Min Act: -0.1700
Data Index: 6033746 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19