Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 675 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0240. Min Range: -7.0240
Max Act: 7.0240. Min Act: -0.1700
Data Index: 5104438 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.9615. Min Act: -0.1700
Data Index: 5553600 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.9615. Min Act: -0.1700
Data Index: 202216 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.9302. Min Act: -0.1700
Data Index: 4612139 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.8990. Min Act: -0.1700
Data Index: 2079620 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.8677. Min Act: -0.1700
Data Index: 6212767 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.8677. Min Act: -0.1700
Data Index: 1716193 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.8677. Min Act: -0.1700
Data Index: 2105158 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.8365. Min Act: -0.1700
Data Index: 1270175 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.8365. Min Act: -0.1700
Data Index: 6119399 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.8365. Min Act: -0.1700
Data Index: 7341669 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.8365. Min Act: -0.1700
Data Index: 3636072 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.7740. Min Act: -0.1700
Data Index: 2130175 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.8052. Min Act: -0.1700
Data Index: 965337 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.8052. Min Act: -0.1700
Data Index: 864155 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.7740. Min Act: -0.1700
Data Index: 1582469 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.7740. Min Act: -0.1700
Data Index: 5401222 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.7740. Min Act: -0.1700
Data Index: 4420846 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.7427. Min Act: -0.1700
Data Index: 1486670 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.7740. Min Act: -0.1700
Data Index: 6177242 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19