Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3093 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.3627. Min Range: -1.3627
Max Act: 1.3627. Min Act: -0.1700
Data Index: 4781229 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3627. Min Range: -1.3627
Max Act: 1.3362. Min Act: -0.1700
Data Index: 4352828 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3627. Min Range: -1.3627
Max Act: 1.3274. Min Act: -0.1700
Data Index: 7645172 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3627. Min Range: -1.3627
Max Act: 1.2833. Min Act: -0.1700
Data Index: 3440698 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3627. Min Range: -1.3627
Max Act: 1.2569. Min Act: -0.1700
Data Index: 2452447 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3627. Min Range: -1.3627
Max Act: 1.2392. Min Act: -0.1700
Data Index: 993047 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3627. Min Range: -1.3627
Max Act: 1.2304. Min Act: -0.1700
Data Index: 2706030 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3627. Min Range: -1.3627
Max Act: 1.2304. Min Act: -0.1700
Data Index: 990340 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3627. Min Range: -1.3627
Max Act: 1.2304. Min Act: -0.1700
Data Index: 3990952 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3627. Min Range: -1.3627
Max Act: 1.2216. Min Act: -0.1699
Data Index: 8334063 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3627. Min Range: -1.3627
Max Act: 1.2216. Min Act: -0.1700
Data Index: 5290892 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3627. Min Range: -1.3627
Max Act: 1.2128. Min Act: -0.1700
Data Index: 4974485 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3627. Min Range: -1.3627
Max Act: 1.2040. Min Act: -0.1700
Data Index: 1736958 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3627. Min Range: -1.3627
Max Act: 1.2040. Min Act: -0.1700
Data Index: 7302383 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3627. Min Range: -1.3627
Max Act: 1.1952. Min Act: -0.1700
Data Index: 168817 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3627. Min Range: -1.3627
Max Act: 1.2040. Min Act: -0.1698
Data Index: 5970286 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3627. Min Range: -1.3627
Max Act: 1.1952. Min Act: -0.1700
Data Index: 1828952 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3627. Min Range: -1.3627
Max Act: 1.2040. Min Act: -0.1700
Data Index: 8541515 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3627. Min Range: -1.3627
Max Act: 1.1952. Min Act: -0.1700
Data Index: 6821117 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3627. Min Range: -1.3627
Max Act: 1.1864. Min Act: -0.1700
Data Index: 8071260 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19