Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2775 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4540. Min Range: -1.4540
Max Act: 1.4540. Min Act: -0.1700
Data Index: 891476 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4540. Min Range: -1.4540
Max Act: 1.4188. Min Act: -0.1700
Data Index: 2039145 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4540. Min Range: -1.4540
Max Act: 1.3836. Min Act: -0.1700
Data Index: 7559229 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4540. Min Range: -1.4540
Max Act: 1.3747. Min Act: -0.1700
Data Index: 2443574 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4540. Min Range: -1.4540
Max Act: 1.3483. Min Act: -0.1700
Data Index: 3591529 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4540. Min Range: -1.4540
Max Act: 1.3395. Min Act: -0.1700
Data Index: 8045604 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4540. Min Range: -1.4540
Max Act: 1.3130. Min Act: -0.1700
Data Index: 7453722 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4540. Min Range: -1.4540
Max Act: 1.3218. Min Act: -0.1700
Data Index: 4692978 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4540. Min Range: -1.4540
Max Act: 1.2954. Min Act: -0.1700
Data Index: 7835879 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4540. Min Range: -1.4540
Max Act: 1.2954. Min Act: -0.1700
Data Index: 5755272 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4540. Min Range: -1.4540
Max Act: 1.2777. Min Act: -0.1700
Data Index: 6493642 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4540. Min Range: -1.4540
Max Act: 1.2601. Min Act: -0.1700
Data Index: 2342481 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4540. Min Range: -1.4540
Max Act: 1.2689. Min Act: -0.1700
Data Index: 6486790 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4540. Min Range: -1.4540
Max Act: 1.2513. Min Act: -0.1700
Data Index: 4081592 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4540. Min Range: -1.4540
Max Act: 1.2513. Min Act: -0.1700
Data Index: 6029578 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4540. Min Range: -1.4540
Max Act: 1.2425. Min Act: -0.1700
Data Index: 3264065 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4540. Min Range: -1.4540
Max Act: 1.2337. Min Act: -0.1700
Data Index: 7967720 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4540. Min Range: -1.4540
Max Act: 1.2248. Min Act: -0.1700
Data Index: 1007314 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4540. Min Range: -1.4540
Max Act: 1.2248. Min Act: -0.1700
Data Index: 995867 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4540. Min Range: -1.4540
Max Act: 1.2248. Min Act: -0.1700
Data Index: 4103512 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19