Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6297 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4624. Min Range: -7.4624
Max Act: 7.4624. Min Act: -0.1700
Data Index: 8102768 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4624. Min Range: -7.4624
Max Act: 7.4311. Min Act: -0.1700
Data Index: 3194498 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4624. Min Range: -7.4624
Max Act: 7.3374. Min Act: -0.1700
Data Index: 3342326 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4624. Min Range: -7.4624
Max Act: 7.0874. Min Act: -0.1700
Data Index: 6594436 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4624. Min Range: -7.4624
Max Act: 7.0249. Min Act: -0.1700
Data Index: 1985351 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4624. Min Range: -7.4624
Max Act: 7.0249. Min Act: -0.1700
Data Index: 3493430 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4624. Min Range: -7.4624
Max Act: 7.0249. Min Act: -0.1700
Data Index: 2187442 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4624. Min Range: -7.4624
Max Act: 6.9311. Min Act: -0.1700
Data Index: 6328095 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4624. Min Range: -7.4624
Max Act: 6.9311. Min Act: -0.1700
Data Index: 6864591 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4624. Min Range: -7.4624
Max Act: 6.9311. Min Act: -0.1700
Data Index: 5258915 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4624. Min Range: -7.4624
Max Act: 6.8374. Min Act: -0.1700
Data Index: 1000844 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4624. Min Range: -7.4624
Max Act: 6.8374. Min Act: -0.1700
Data Index: 8232128 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4624. Min Range: -7.4624
Max Act: 6.8061. Min Act: -0.1700
Data Index: 742644 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4624. Min Range: -7.4624
Max Act: 6.8061. Min Act: -0.1700
Data Index: 7767417 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4624. Min Range: -7.4624
Max Act: 6.7749. Min Act: -0.1700
Data Index: 2585252 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4624. Min Range: -7.4624
Max Act: 6.7436. Min Act: -0.1700
Data Index: 4081664 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4624. Min Range: -7.4624
Max Act: 6.7436. Min Act: -0.1700
Data Index: 4430231 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4624. Min Range: -7.4624
Max Act: 6.7124. Min Act: -0.1700
Data Index: 1339560 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4624. Min Range: -7.4624
Max Act: 6.6811. Min Act: -0.1700
Data Index: 886032 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4624. Min Range: -7.4624
Max Act: 6.6499. Min Act: -0.1700
Data Index: 351229 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19