Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6286 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0095. Min Range: -5.0095
Max Act: 5.0095. Min Act: -0.1700
Data Index: 3218176 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0095. Min Range: -5.0095
Max Act: 4.9470. Min Act: -0.1700
Data Index: 5593216 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0095. Min Range: -5.0095
Max Act: 4.8533. Min Act: -0.1700
Data Index: 2698983 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0095. Min Range: -5.0095
Max Act: 4.8533. Min Act: -0.1700
Data Index: 3005422 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0095. Min Range: -5.0095
Max Act: 4.8220. Min Act: -0.1700
Data Index: 1132495 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0095. Min Range: -5.0095
Max Act: 4.7595. Min Act: -0.1700
Data Index: 5680176 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0095. Min Range: -5.0095
Max Act: 4.7595. Min Act: -0.1700
Data Index: 2659189 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0095. Min Range: -5.0095
Max Act: 4.7283. Min Act: -0.1700
Data Index: 5772457 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0095. Min Range: -5.0095
Max Act: 4.7283. Min Act: -0.1700
Data Index: 4589532 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0095. Min Range: -5.0095
Max Act: 4.7595. Min Act: -0.1700
Data Index: 8664196 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0095. Min Range: -5.0095
Max Act: 4.7283. Min Act: -0.1700
Data Index: 5044582 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0095. Min Range: -5.0095
Max Act: 4.7595. Min Act: -0.1700
Data Index: 1793905 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0095. Min Range: -5.0095
Max Act: 4.6970. Min Act: -0.1700
Data Index: 8730425 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0095. Min Range: -5.0095
Max Act: 4.6970. Min Act: -0.1700
Data Index: 368556 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0095. Min Range: -5.0095
Max Act: 4.6970. Min Act: -0.1700
Data Index: 7388912 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0095. Min Range: -5.0095
Max Act: 4.6658. Min Act: -0.1700
Data Index: 3435635 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0095. Min Range: -5.0095
Max Act: 4.6970. Min Act: -0.1700
Data Index: 7710939 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0095. Min Range: -5.0095
Max Act: 4.6970. Min Act: -0.1700
Data Index: 4351430 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0095. Min Range: -5.0095
Max Act: 4.6970. Min Act: -0.1700
Data Index: 2023397 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0095. Min Range: -5.0095
Max Act: 4.6658. Min Act: -0.1700
Data Index: 7098844 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19