Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2698 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0595. Min Range: -8.0595
Max Act: 8.0595. Min Act: -0.1700
Data Index: 4727396 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0595. Min Range: -8.0595
Max Act: 7.9970. Min Act: -0.1700
Data Index: 4123923 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0595. Min Range: -8.0595
Max Act: 7.9345. Min Act: -0.1700
Data Index: 4140414 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0595. Min Range: -8.0595
Max Act: 7.6845. Min Act: -0.1700
Data Index: 221087 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0595. Min Range: -8.0595
Max Act: 7.7470. Min Act: -0.1700
Data Index: 910821 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0595. Min Range: -8.0595
Max Act: 7.7470. Min Act: -0.1700
Data Index: 1610040 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0595. Min Range: -8.0595
Max Act: 7.7470. Min Act: -0.1700
Data Index: 4978945 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0595. Min Range: -8.0595
Max Act: 7.6845. Min Act: -0.1700
Data Index: 7122410 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0595. Min Range: -8.0595
Max Act: 7.6220. Min Act: -0.1700
Data Index: 3416602 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0595. Min Range: -8.0595
Max Act: 7.6220. Min Act: -0.1700
Data Index: 5390641 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0595. Min Range: -8.0595
Max Act: 7.5595. Min Act: -0.1700
Data Index: 7565974 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0595. Min Range: -8.0595
Max Act: 7.5595. Min Act: -0.1700
Data Index: 7138039 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0595. Min Range: -8.0595
Max Act: 7.5595. Min Act: -0.1700
Data Index: 2633084 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0595. Min Range: -8.0595
Max Act: 7.4970. Min Act: -0.1700
Data Index: 2605825 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0595. Min Range: -8.0595
Max Act: 7.4970. Min Act: -0.1700
Data Index: 6255761 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0595. Min Range: -8.0595
Max Act: 7.4658. Min Act: -0.1700
Data Index: 1219741 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0595. Min Range: -8.0595
Max Act: 7.4970. Min Act: -0.1700
Data Index: 7077187 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0595. Min Range: -8.0595
Max Act: 7.4658. Min Act: -0.1700
Data Index: 7058345 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0595. Min Range: -8.0595
Max Act: 7.4658. Min Act: -0.1700
Data Index: 4978944 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0595. Min Range: -8.0595
Max Act: 7.4345. Min Act: -0.1700
Data Index: 540252 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19