Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3182 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2332. Min Range: -3.2332
Max Act: 3.2332. Min Act: -0.1700
Data Index: 2643842 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2332. Min Range: -3.2332
Max Act: 3.1703. Min Act: -0.1700
Data Index: 4182749 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2332. Min Range: -3.2332
Max Act: 3.1230. Min Act: -0.1700
Data Index: 8432564 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2332. Min Range: -3.2332
Max Act: 3.1073. Min Act: -0.1700
Data Index: 7670718 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2332. Min Range: -3.2332
Max Act: 3.0126. Min Act: -0.1700
Data Index: 1680746 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2332. Min Range: -3.2332
Max Act: 3.0284. Min Act: -0.1700
Data Index: 3025640 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2332. Min Range: -3.2332
Max Act: 3.0442. Min Act: -0.1700
Data Index: 3260642 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2332. Min Range: -3.2332
Max Act: 3.0284. Min Act: -0.1700
Data Index: 5513945 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2332. Min Range: -3.2332
Max Act: 3.0284. Min Act: -0.1700
Data Index: 3430107 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2332. Min Range: -3.2332
Max Act: 3.0126. Min Act: -0.1700
Data Index: 6053727 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2332. Min Range: -3.2332
Max Act: 3.0284. Min Act: -0.1700
Data Index: 4072639 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2332. Min Range: -3.2332
Max Act: 2.9968. Min Act: -0.1700
Data Index: 7975771 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2332. Min Range: -3.2332
Max Act: 2.9652. Min Act: -0.1700
Data Index: 4074567 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2332. Min Range: -3.2332
Max Act: 2.9652. Min Act: -0.1700
Data Index: 5818853 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2332. Min Range: -3.2332
Max Act: 2.9652. Min Act: -0.1700
Data Index: 8291903 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2332. Min Range: -3.2332
Max Act: 2.9652. Min Act: -0.1700
Data Index: 7371752 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2332. Min Range: -3.2332
Max Act: 2.9494. Min Act: -0.1700
Data Index: 5317488 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2332. Min Range: -3.2332
Max Act: 2.9494. Min Act: -0.1700
Data Index: 1736685 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2332. Min Range: -3.2332
Max Act: 2.9652. Min Act: -0.1700
Data Index: 1680744 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2332. Min Range: -3.2332
Max Act: 2.9335. Min Act: -0.1700
Data Index: 3292805 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19