Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2440 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7125. Min Range: -2.7125
Max Act: 2.7125. Min Act: -0.1700
Data Index: 7301407 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7125. Min Range: -2.7125
Max Act: 2.6805. Min Act: -0.1700
Data Index: 1484815 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7125. Min Range: -2.7125
Max Act: 2.6805. Min Act: -0.1700
Data Index: 2534113 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7125. Min Range: -2.7125
Max Act: 2.6484. Min Act: -0.1700
Data Index: 5718821 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7125. Min Range: -2.7125
Max Act: 2.6645. Min Act: -0.1700
Data Index: 6861316 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7125. Min Range: -2.7125
Max Act: 2.6163. Min Act: -0.1700
Data Index: 6038778 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7125. Min Range: -2.7125
Max Act: 2.6163. Min Act: -0.1700
Data Index: 98738 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7125. Min Range: -2.7125
Max Act: 2.6002. Min Act: -0.1700
Data Index: 3604192 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7125. Min Range: -2.7125
Max Act: 2.5841. Min Act: -0.1700
Data Index: 7746941 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7125. Min Range: -2.7125
Max Act: 2.5841. Min Act: -0.1700
Data Index: 2246477 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7125. Min Range: -2.7125
Max Act: 2.5841. Min Act: -0.1700
Data Index: 289567 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7125. Min Range: -2.7125
Max Act: 2.5680. Min Act: -0.1700
Data Index: 4971248 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7125. Min Range: -2.7125
Max Act: 2.5519. Min Act: -0.1700
Data Index: 8707823 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7125. Min Range: -2.7125
Max Act: 2.5680. Min Act: -0.1700
Data Index: 7963947 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7125. Min Range: -2.7125
Max Act: 2.5680. Min Act: -0.1700
Data Index: 3676554 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7125. Min Range: -2.7125
Max Act: 2.5680. Min Act: -0.1700
Data Index: 4143735 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7125. Min Range: -2.7125
Max Act: 2.5680. Min Act: -0.1700
Data Index: 98739 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7125. Min Range: -2.7125
Max Act: 2.5357. Min Act: -0.1700
Data Index: 6578082 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7125. Min Range: -2.7125
Max Act: 2.5519. Min Act: -0.1700
Data Index: 4414985 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7125. Min Range: -2.7125
Max Act: 2.5519. Min Act: -0.1700
Data Index: 3578705 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19