Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3648 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6882. Min Range: -5.6882
Max Act: 5.6882. Min Act: -0.1694
Data Index: 4733156 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6882. Min Range: -5.6882
Max Act: 5.4382. Min Act: -0.1700
Data Index: 4074743 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6882. Min Range: -5.6882
Max Act: 5.4382. Min Act: -0.1700
Data Index: 1565094 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6882. Min Range: -5.6882
Max Act: 5.2194. Min Act: -0.1700
Data Index: 3976167 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6882. Min Range: -5.6882
Max Act: 5.2194. Min Act: -0.1700
Data Index: 759838 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6882. Min Range: -5.6882
Max Act: 5.2194. Min Act: -0.1700
Data Index: 5185346 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6882. Min Range: -5.6882
Max Act: 5.2819. Min Act: -0.1700
Data Index: 8696085 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6882. Min Range: -5.6882
Max Act: 5.1882. Min Act: -0.1700
Data Index: 4960816 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6882. Min Range: -5.6882
Max Act: 5.1569. Min Act: -0.1700
Data Index: 5873755 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6882. Min Range: -5.6882
Max Act: 5.1257. Min Act: -0.1700
Data Index: 6449053 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6882. Min Range: -5.6882
Max Act: 5.0944. Min Act: -0.1700
Data Index: 2232039 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6882. Min Range: -5.6882
Max Act: 5.0944. Min Act: -0.1700
Data Index: 6805063 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6882. Min Range: -5.6882
Max Act: 5.1257. Min Act: -0.1699
Data Index: 326753 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6882. Min Range: -5.6882
Max Act: 5.0944. Min Act: -0.1700
Data Index: 7780253 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6882. Min Range: -5.6882
Max Act: 5.0319. Min Act: -0.1700
Data Index: 82089 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6882. Min Range: -5.6882
Max Act: 5.0944. Min Act: -0.1700
Data Index: 917017 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6882. Min Range: -5.6882
Max Act: 5.0632. Min Act: -0.1700
Data Index: 1675245 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6882. Min Range: -5.6882
Max Act: 5.0632. Min Act: -0.1700
Data Index: 1677543 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6882. Min Range: -5.6882
Max Act: 5.0944. Min Act: -0.1700
Data Index: 4785958 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6882. Min Range: -5.6882
Max Act: 5.0632. Min Act: -0.1700
Data Index: 4870011 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19