Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 593 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9129. Min Range: -5.9129
Max Act: 5.9129. Min Act: -0.1700
Data Index: 8287267 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9129. Min Range: -5.9129
Max Act: 5.8817. Min Act: -0.1700
Data Index: 3428605 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9129. Min Range: -5.9129
Max Act: 5.7879. Min Act: -0.1700
Data Index: 3177021 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9129. Min Range: -5.9129
Max Act: 5.7254. Min Act: -0.1700
Data Index: 1423823 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9129. Min Range: -5.9129
Max Act: 5.6942. Min Act: -0.1700
Data Index: 6825421 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9129. Min Range: -5.9129
Max Act: 5.6629. Min Act: -0.1700
Data Index: 1155980 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9129. Min Range: -5.9129
Max Act: 5.6317. Min Act: -0.1700
Data Index: 4665529 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9129. Min Range: -5.9129
Max Act: 5.6317. Min Act: -0.1700
Data Index: 8287266 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9129. Min Range: -5.9129
Max Act: 5.6004. Min Act: -0.1700
Data Index: 1291580 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9129. Min Range: -5.9129
Max Act: 5.6004. Min Act: -0.1700
Data Index: 8750177 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9129. Min Range: -5.9129
Max Act: 5.6004. Min Act: -0.1700
Data Index: 2592383 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9129. Min Range: -5.9129
Max Act: 5.5692. Min Act: -0.1700
Data Index: 5009154 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9129. Min Range: -5.9129
Max Act: 5.5692. Min Act: -0.1700
Data Index: 600565 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9129. Min Range: -5.9129
Max Act: 5.5692. Min Act: -0.1700
Data Index: 305629 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9129. Min Range: -5.9129
Max Act: 5.5692. Min Act: -0.1700
Data Index: 286028 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9129. Min Range: -5.9129
Max Act: 5.5692. Min Act: -0.1700
Data Index: 4244866 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9129. Min Range: -5.9129
Max Act: 5.5692. Min Act: -0.1700
Data Index: 6531901 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9129. Min Range: -5.9129
Max Act: 5.5692. Min Act: -0.1700
Data Index: 6155146 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9129. Min Range: -5.9129
Max Act: 5.5379. Min Act: -0.1700
Data Index: 4992494 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9129. Min Range: -5.9129
Max Act: 5.5692. Min Act: -0.1700
Data Index: 33284 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19