Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2517 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.7442. Min Act: -0.1700
Data Index: 5047651 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.7442. Min Act: -0.1700
Data Index: 5394504 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.7442. Min Act: -0.1700
Data Index: 5170812 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.6817. Min Act: -0.1700
Data Index: 1094668 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.5879. Min Act: -0.1700
Data Index: 6057294 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.5879. Min Act: -0.1700
Data Index: 3145339 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.5567. Min Act: -0.1700
Data Index: 5963527 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.5567. Min Act: -0.1700
Data Index: 7264934 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.4942. Min Act: -0.1700
Data Index: 7638758 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.4942. Min Act: -0.1700
Data Index: 542774 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.4942. Min Act: -0.1700
Data Index: 1557764 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.4629. Min Act: -0.1700
Data Index: 2389084 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.4317. Min Act: -0.1700
Data Index: 3063507 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.4004. Min Act: -0.1700
Data Index: 8472713 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.4004. Min Act: -0.1700
Data Index: 1587508 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.3692. Min Act: -0.1700
Data Index: 6804287 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.3692. Min Act: -0.1700
Data Index: 6027078 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.3379. Min Act: -0.1700
Data Index: 233287 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.3379. Min Act: -0.1700
Data Index: 6628516 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.3379. Min Act: -0.1700
Data Index: 2486141 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19