Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1714 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3989. Min Range: -9.3989
Max Act: 9.3989. Min Act: -0.1700
Data Index: 5204490 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3989. Min Range: -9.3989
Max Act: 9.1489. Min Act: -0.1700
Data Index: 8173892 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3989. Min Range: -9.3989
Max Act: 8.9614. Min Act: -0.1700
Data Index: 3159930 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3989. Min Range: -9.3989
Max Act: 8.8989. Min Act: -0.1700
Data Index: 1867567 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3989. Min Range: -9.3989
Max Act: 8.8989. Min Act: -0.1700
Data Index: 3159935 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3989. Min Range: -9.3989
Max Act: 8.7739. Min Act: -0.1700
Data Index: 5877045 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3989. Min Range: -9.3989
Max Act: 8.6489. Min Act: -0.1700
Data Index: 1867563 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3989. Min Range: -9.3989
Max Act: 8.6489. Min Act: -0.1700
Data Index: 5666627 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3989. Min Range: -9.3989
Max Act: 8.5864. Min Act: -0.1700
Data Index: 1671642 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3989. Min Range: -9.3989
Max Act: 8.5864. Min Act: -0.1700
Data Index: 6543207 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3989. Min Range: -9.3989
Max Act: 8.5864. Min Act: -0.1700
Data Index: 1671643 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3989. Min Range: -9.3989
Max Act: 8.5864. Min Act: -0.1700
Data Index: 2677520 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3989. Min Range: -9.3989
Max Act: 8.5239. Min Act: -0.1700
Data Index: 5356434 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3989. Min Range: -9.3989
Max Act: 8.5239. Min Act: -0.1700
Data Index: 66991 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3989. Min Range: -9.3989
Max Act: 8.5239. Min Act: -0.1700
Data Index: 4417578 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3989. Min Range: -9.3989
Max Act: 8.5239. Min Act: -0.1700
Data Index: 1781177 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3989. Min Range: -9.3989
Max Act: 8.5864. Min Act: -0.1700
Data Index: 2346139 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3989. Min Range: -9.3989
Max Act: 8.5239. Min Act: -0.1700
Data Index: 332434 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3989. Min Range: -9.3989
Max Act: 8.5239. Min Act: -0.1700
Data Index: 8153687 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3989. Min Range: -9.3989
Max Act: 8.4614. Min Act: -0.1700
Data Index: 7287502 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19