Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3820 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3605. Min Range: -4.3605
Max Act: 4.3292. Min Act: -0.1700
Data Index: 5892439 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3605. Min Range: -4.3605
Max Act: 4.3605. Min Act: -0.1700
Data Index: 8302192 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3605. Min Range: -4.3605
Max Act: 4.2980. Min Act: -0.1700
Data Index: 5222406 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3605. Min Range: -4.3605
Max Act: 4.2667. Min Act: -0.1700
Data Index: 7281428 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3605. Min Range: -4.3605
Max Act: 4.2667. Min Act: -0.1700
Data Index: 5292143 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3605. Min Range: -4.3605
Max Act: 4.2667. Min Act: -0.1700
Data Index: 2525358 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3605. Min Range: -4.3605
Max Act: 4.2355. Min Act: -0.1700
Data Index: 7105978 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3605. Min Range: -4.3605
Max Act: 4.2042. Min Act: -0.1700
Data Index: 7149664 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3605. Min Range: -4.3605
Max Act: 4.2355. Min Act: -0.1700
Data Index: 3577926 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3605. Min Range: -4.3605
Max Act: 4.2355. Min Act: -0.1700
Data Index: 2822480 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3605. Min Range: -4.3605
Max Act: 4.2042. Min Act: -0.1700
Data Index: 5479837 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3605. Min Range: -4.3605
Max Act: 4.2355. Min Act: -0.1700
Data Index: 1613853 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3605. Min Range: -4.3605
Max Act: 4.2355. Min Act: -0.1700
Data Index: 8002082 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3605. Min Range: -4.3605
Max Act: 4.2355. Min Act: -0.1700
Data Index: 7506666 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3605. Min Range: -4.3605
Max Act: 4.2355. Min Act: -0.1700
Data Index: 4435216 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3605. Min Range: -4.3605
Max Act: 4.2042. Min Act: -0.1700
Data Index: 5615011 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3605. Min Range: -4.3605
Max Act: 4.2042. Min Act: -0.1700
Data Index: 3034623 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3605. Min Range: -4.3605
Max Act: 4.2042. Min Act: -0.1700
Data Index: 5635967 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3605. Min Range: -4.3605
Max Act: 4.2042. Min Act: -0.1700
Data Index: 6724377 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3605. Min Range: -4.3605
Max Act: 4.2042. Min Act: -0.1700
Data Index: 6865097 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19