Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 750 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.5113. Min Range: -0.5113
Max Act: 0.5113. Min Act: -0.1698
Data Index: 3001860 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5113. Min Range: -0.5113
Max Act: 0.4814. Min Act: -0.1700
Data Index: 1336697 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5113. Min Range: -0.5113
Max Act: 0.4739. Min Act: -0.1700
Data Index: 2184447 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5113. Min Range: -0.5113
Max Act: 0.4665. Min Act: -0.1699
Data Index: 6049344 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5113. Min Range: -0.5113
Max Act: 0.4665. Min Act: -0.1700
Data Index: 2923107 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5113. Min Range: -0.5113
Max Act: 0.4446. Min Act: -0.1700
Data Index: 5225722 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5113. Min Range: -0.5113
Max Act: 0.4446. Min Act: -0.1700
Data Index: 4466510 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5113. Min Range: -0.5113
Max Act: 0.4446. Min Act: -0.1700
Data Index: 254789 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5113. Min Range: -0.5113
Max Act: 0.4446. Min Act: -0.1678
Data Index: 5378011 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5113. Min Range: -0.5113
Max Act: 0.4373. Min Act: -0.1700
Data Index: 4695272 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5113. Min Range: -0.5113
Max Act: 0.4373. Min Act: -0.1653
Data Index: 2981671 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5113. Min Range: -0.5113
Max Act: 0.4301. Min Act: -0.1696
Data Index: 296382 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5113. Min Range: -0.5113
Max Act: 0.4301. Min Act: -0.1653
Data Index: 6660903 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5113. Min Range: -0.5113
Max Act: 0.4301. Min Act: -0.1699
Data Index: 2550040 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5113. Min Range: -0.5113
Max Act: 0.4229. Min Act: -0.1698
Data Index: 3268969 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5113. Min Range: -0.5113
Max Act: 0.4229. Min Act: -0.1690
Data Index: 2640457 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5113. Min Range: -0.5113
Max Act: 0.4158. Min Act: -0.1693
Data Index: 8275902 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5113. Min Range: -0.5113
Max Act: 0.4086. Min Act: -0.1700
Data Index: 783800 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5113. Min Range: -0.5113
Max Act: 0.4086. Min Act: -0.1700
Data Index: 7216627 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5113. Min Range: -0.5113
Max Act: 0.4086. Min Act: -0.1698
Data Index: 6105089 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19