Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 47 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4101. Min Range: -4.4101
Max Act: 4.4101. Min Act: -0.1700
Data Index: 4368705 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4101. Min Range: -4.4101
Max Act: 4.2538. Min Act: -0.1700
Data Index: 6254307 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4101. Min Range: -4.4101
Max Act: 4.2538. Min Act: -0.1700
Data Index: 650437 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4101. Min Range: -4.4101
Max Act: 4.1913. Min Act: -0.1700
Data Index: 8117710 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4101. Min Range: -4.4101
Max Act: 4.1913. Min Act: -0.1700
Data Index: 1459446 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4101. Min Range: -4.4101
Max Act: 4.1601. Min Act: -0.1700
Data Index: 2262029 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4101. Min Range: -4.4101
Max Act: 4.0976. Min Act: -0.1700
Data Index: 1208686 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4101. Min Range: -4.4101
Max Act: 4.1288. Min Act: -0.1700
Data Index: 8117352 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4101. Min Range: -4.4101
Max Act: 4.0976. Min Act: -0.1700
Data Index: 1202742 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4101. Min Range: -4.4101
Max Act: 4.0976. Min Act: -0.1700
Data Index: 8458974 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4101. Min Range: -4.4101
Max Act: 4.0351. Min Act: -0.1700
Data Index: 2667643 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4101. Min Range: -4.4101
Max Act: 4.0663. Min Act: -0.1700
Data Index: 1125950 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4101. Min Range: -4.4101
Max Act: 4.0663. Min Act: -0.1700
Data Index: 4368707 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4101. Min Range: -4.4101
Max Act: 4.0663. Min Act: -0.1700
Data Index: 1676165 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4101. Min Range: -4.4101
Max Act: 4.0663. Min Act: -0.1700
Data Index: 7196065 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4101. Min Range: -4.4101
Max Act: 4.0038. Min Act: -0.1700
Data Index: 7388640 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4101. Min Range: -4.4101
Max Act: 4.0351. Min Act: -0.1700
Data Index: 3858920 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4101. Min Range: -4.4101
Max Act: 4.0351. Min Act: -0.1700
Data Index: 7133948 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4101. Min Range: -4.4101
Max Act: 4.0351. Min Act: -0.1700
Data Index: 2182679 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4101. Min Range: -4.4101
Max Act: 4.0351. Min Act: -0.1700
Data Index: 5070880 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19