Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 71 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0333. Min Range: -7.0333
Max Act: 7.0333. Min Act: -0.1700
Data Index: 1840780 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0333. Min Range: -7.0333
Max Act: 6.8771. Min Act: -0.1700
Data Index: 5717684 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0333. Min Range: -7.0333
Max Act: 6.8771. Min Act: -0.1700
Data Index: 2065464 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0333. Min Range: -7.0333
Max Act: 6.8771. Min Act: -0.1700
Data Index: 2721232 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0333. Min Range: -7.0333
Max Act: 6.8771. Min Act: -0.1700
Data Index: 8612174 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0333. Min Range: -7.0333
Max Act: 6.7833. Min Act: -0.1700
Data Index: 36774 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0333. Min Range: -7.0333
Max Act: 6.8146. Min Act: -0.1700
Data Index: 3983065 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0333. Min Range: -7.0333
Max Act: 6.7833. Min Act: -0.1700
Data Index: 1949719 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0333. Min Range: -7.0333
Max Act: 6.7521. Min Act: -0.1700
Data Index: 3835063 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0333. Min Range: -7.0333
Max Act: 6.7833. Min Act: -0.1700
Data Index: 3123162 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0333. Min Range: -7.0333
Max Act: 6.7208. Min Act: -0.1698
Data Index: 8805483 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0333. Min Range: -7.0333
Max Act: 6.7208. Min Act: -0.1700
Data Index: 5701453 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0333. Min Range: -7.0333
Max Act: 6.7208. Min Act: -0.1700
Data Index: 3970596 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0333. Min Range: -7.0333
Max Act: 6.6896. Min Act: -0.1700
Data Index: 1323678 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0333. Min Range: -7.0333
Max Act: 6.6896. Min Act: -0.1700
Data Index: 4864186 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0333. Min Range: -7.0333
Max Act: 6.6896. Min Act: -0.1700
Data Index: 7542954 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0333. Min Range: -7.0333
Max Act: 6.6896. Min Act: -0.1700
Data Index: 7631551 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0333. Min Range: -7.0333
Max Act: 6.6896. Min Act: -0.1700
Data Index: 6571090 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0333. Min Range: -7.0333
Max Act: 6.6896. Min Act: -0.1700
Data Index: 3017359 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0333. Min Range: -7.0333
Max Act: 6.6583. Min Act: -0.1700
Data Index: 6270135 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19