Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2521 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7295. Min Range: -9.7295
Max Act: 9.7295. Min Act: -0.1700
Data Index: 1106435 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7295. Min Range: -9.7295
Max Act: 9.6670. Min Act: -0.1700
Data Index: 4474969 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7295. Min Range: -9.7295
Max Act: 9.7295. Min Act: -0.1700
Data Index: 5006678 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7295. Min Range: -9.7295
Max Act: 9.6670. Min Act: -0.1700
Data Index: 3714409 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7295. Min Range: -9.7295
Max Act: 9.6045. Min Act: -0.1700
Data Index: 8119322 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7295. Min Range: -9.7295
Max Act: 9.4170. Min Act: -0.1700
Data Index: 3164427 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7295. Min Range: -9.7295
Max Act: 9.4170. Min Act: -0.1700
Data Index: 8077883 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7295. Min Range: -9.7295
Max Act: 9.3545. Min Act: -0.1700
Data Index: 6610887 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7295. Min Range: -9.7295
Max Act: 9.3545. Min Act: -0.1700
Data Index: 157849 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7295. Min Range: -9.7295
Max Act: 9.3545. Min Act: -0.1700
Data Index: 6267184 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7295. Min Range: -9.7295
Max Act: 9.2920. Min Act: -0.1700
Data Index: 3918239 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7295. Min Range: -9.7295
Max Act: 9.2920. Min Act: -0.1700
Data Index: 5191839 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7295. Min Range: -9.7295
Max Act: 9.2295. Min Act: -0.1700
Data Index: 481322 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7295. Min Range: -9.7295
Max Act: 9.1670. Min Act: -0.1700
Data Index: 2406472 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7295. Min Range: -9.7295
Max Act: 9.2295. Min Act: -0.1700
Data Index: 4469627 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7295. Min Range: -9.7295
Max Act: 9.2295. Min Act: -0.1700
Data Index: 172050 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7295. Min Range: -9.7295
Max Act: 9.1670. Min Act: -0.1700
Data Index: 7806396 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7295. Min Range: -9.7295
Max Act: 9.2295. Min Act: -0.1700
Data Index: 5842090 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7295. Min Range: -9.7295
Max Act: 9.1045. Min Act: -0.1700
Data Index: 4939160 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7295. Min Range: -9.7295
Max Act: 9.1045. Min Act: -0.1700
Data Index: 7319227 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19