Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2696 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.4295. Min Act: -0.1700
Data Index: 3768192 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.3983. Min Act: -0.1700
Data Index: 3742450 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.3045. Min Act: -0.1700
Data Index: 1224232 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.2733. Min Act: -0.1700
Data Index: 1205738 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.2420. Min Act: -0.1700
Data Index: 8061196 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.2420. Min Act: -0.1700
Data Index: 1515719 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.1483. Min Act: -0.1700
Data Index: 8730770 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.1483. Min Act: -0.1700
Data Index: 6757892 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.1170. Min Act: -0.1700
Data Index: 4787430 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.1483. Min Act: -0.1700
Data Index: 8757559 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.1483. Min Act: -0.1700
Data Index: 6264832 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.1483. Min Act: -0.1700
Data Index: 1736534 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.1170. Min Act: -0.1700
Data Index: 4286057 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.1170. Min Act: -0.1700
Data Index: 4023332 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.1170. Min Act: -0.1700
Data Index: 1967073 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.0858. Min Act: -0.1700
Data Index: 2682535 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.0858. Min Act: -0.1700
Data Index: 7934420 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.0858. Min Act: -0.1700
Data Index: 1008410 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.0545. Min Act: -0.1700
Data Index: 3852453 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.0545. Min Act: -0.1700
Data Index: 6889897 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19