Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1238 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9033. Min Range: -5.9033
Max Act: 5.9033. Min Act: -0.1700
Data Index: 4744057 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9033. Min Range: -5.9033
Max Act: 5.9033. Min Act: -0.1700
Data Index: 4744054 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9033. Min Range: -5.9033
Max Act: 5.8408. Min Act: -0.1700
Data Index: 4744059 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9033. Min Range: -5.9033
Max Act: 5.8095. Min Act: -0.1700
Data Index: 4744053 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9033. Min Range: -5.9033
Max Act: 5.8095. Min Act: -0.1700
Data Index: 4744056 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9033. Min Range: -5.9033
Max Act: 5.7470. Min Act: -0.1700
Data Index: 8550268 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9033. Min Range: -5.9033
Max Act: 5.7783. Min Act: -0.1700
Data Index: 4744042 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9033. Min Range: -5.9033
Max Act: 5.7158. Min Act: -0.1700
Data Index: 4141568 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9033. Min Range: -5.9033
Max Act: 5.6220. Min Act: -0.1700
Data Index: 2011659 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9033. Min Range: -5.9033
Max Act: 5.5908. Min Act: -0.1700
Data Index: 60411 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9033. Min Range: -5.9033
Max Act: 5.5595. Min Act: -0.1700
Data Index: 4744058 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9033. Min Range: -5.9033
Max Act: 5.5908. Min Act: -0.1700
Data Index: 4744055 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9033. Min Range: -5.9033
Max Act: 5.5283. Min Act: -0.1700
Data Index: 6066619 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9033. Min Range: -5.9033
Max Act: 5.4970. Min Act: -0.1700
Data Index: 4327490 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9033. Min Range: -5.9033
Max Act: 5.4658. Min Act: -0.1700
Data Index: 4327498 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9033. Min Range: -5.9033
Max Act: 5.4970. Min Act: -0.1700
Data Index: 3213679 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9033. Min Range: -5.9033
Max Act: 5.4970. Min Act: -0.1700
Data Index: 3364526 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9033. Min Range: -5.9033
Max Act: 5.4970. Min Act: -0.1700
Data Index: 6066631 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9033. Min Range: -5.9033
Max Act: 5.4970. Min Act: -0.1700
Data Index: 4327499 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9033. Min Range: -5.9033
Max Act: 5.5283. Min Act: -0.1700
Data Index: 4327500 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19