Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6060 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9874. Min Range: -1.9874
Max Act: 1.9874. Min Act: -0.1680
Data Index: 7042242 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9874. Min Range: -1.9874
Max Act: 1.9874. Min Act: -0.1656
Data Index: 2704305 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9874. Min Range: -1.9874
Max Act: 1.9535. Min Act: -0.1659
Data Index: 3284986 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9874. Min Range: -1.9874
Max Act: 1.9535. Min Act: -0.1690
Data Index: 6691687 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9874. Min Range: -1.9874
Max Act: 1.9365. Min Act: -0.1549
Data Index: 2289380 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9874. Min Range: -1.9874
Max Act: 1.9365. Min Act: -0.1694
Data Index: 2933147 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9874. Min Range: -1.9874
Max Act: 1.9195. Min Act: -0.1700
Data Index: 811940 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9874. Min Range: -1.9874
Max Act: 1.9195. Min Act: -0.1699
Data Index: 152164 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9874. Min Range: -1.9874
Max Act: 1.9195. Min Act: -0.1626
Data Index: 7793518 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9874. Min Range: -1.9874
Max Act: 1.9195. Min Act: -0.1653
Data Index: 3205764 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9874. Min Range: -1.9874
Max Act: 1.9024. Min Act: -0.1700
Data Index: 4443146 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9874. Min Range: -1.9874
Max Act: 1.9024. Min Act: -0.1682
Data Index: 671516 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9874. Min Range: -1.9874
Max Act: 1.9024. Min Act: -0.1670
Data Index: 2417550 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9874. Min Range: -1.9874
Max Act: 1.9024. Min Act: -0.1700
Data Index: 7415016 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9874. Min Range: -1.9874
Max Act: 1.9024. Min Act: -0.1699
Data Index: 5181412 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9874. Min Range: -1.9874
Max Act: 1.9024. Min Act: -0.1691
Data Index: 4551072 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9874. Min Range: -1.9874
Max Act: 1.8939. Min Act: -0.1691
Data Index: 4140935 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9874. Min Range: -1.9874
Max Act: 1.8939. Min Act: -0.1700
Data Index: 4163102 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9874. Min Range: -1.9874
Max Act: 1.8939. Min Act: -0.1676
Data Index: 4489104 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9874. Min Range: -1.9874
Max Act: 1.9024. Min Act: -0.1700
Data Index: 4543566 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19