Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2735 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0897. Min Range: -7.0897
Max Act: 7.0897. Min Act: -0.1700
Data Index: 7044341 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0897. Min Range: -7.0897
Max Act: 7.0585. Min Act: -0.1700
Data Index: 5666917 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0897. Min Range: -7.0897
Max Act: 6.9647. Min Act: -0.1700
Data Index: 7765652 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0897. Min Range: -7.0897
Max Act: 6.8710. Min Act: -0.1700
Data Index: 8650999 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0897. Min Range: -7.0897
Max Act: 6.8710. Min Act: -0.1700
Data Index: 6781674 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0897. Min Range: -7.0897
Max Act: 6.7147. Min Act: -0.1700
Data Index: 6933193 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0897. Min Range: -7.0897
Max Act: 6.7147. Min Act: -0.1700
Data Index: 2440581 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0897. Min Range: -7.0897
Max Act: 6.6835. Min Act: -0.1700
Data Index: 2479370 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0897. Min Range: -7.0897
Max Act: 6.7147. Min Act: -0.1700
Data Index: 7614507 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0897. Min Range: -7.0897
Max Act: 6.6835. Min Act: -0.1700
Data Index: 853654 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0897. Min Range: -7.0897
Max Act: 6.6835. Min Act: -0.1700
Data Index: 3169256 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0897. Min Range: -7.0897
Max Act: 6.7147. Min Act: -0.1700
Data Index: 4710668 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0897. Min Range: -7.0897
Max Act: 6.6835. Min Act: -0.1700
Data Index: 203474 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0897. Min Range: -7.0897
Max Act: 6.6522. Min Act: -0.1700
Data Index: 4464774 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0897. Min Range: -7.0897
Max Act: 6.6522. Min Act: -0.1700
Data Index: 2521697 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0897. Min Range: -7.0897
Max Act: 6.6522. Min Act: -0.1700
Data Index: 520512 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0897. Min Range: -7.0897
Max Act: 6.6522. Min Act: -0.1700
Data Index: 8577075 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0897. Min Range: -7.0897
Max Act: 6.6210. Min Act: -0.1700
Data Index: 6633266 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0897. Min Range: -7.0897
Max Act: 6.6210. Min Act: -0.1700
Data Index: 2867263 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0897. Min Range: -7.0897
Max Act: 6.5897. Min Act: -0.1700
Data Index: 6837234 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19