Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2974 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.9735. Min Act: -0.1700
Data Index: 25673 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.7860. Min Act: -0.1700
Data Index: 8632653 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.6923. Min Act: -0.1700
Data Index: 251599 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.5985. Min Act: -0.1700
Data Index: 7976957 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.5048. Min Act: -0.1700
Data Index: 8799256 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.4423. Min Act: -0.1700
Data Index: 995987 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.3798. Min Act: -0.1700
Data Index: 221937 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.3173. Min Act: -0.1700
Data Index: 1114371 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.3485. Min Act: -0.1700
Data Index: 3688928 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.3173. Min Act: -0.1700
Data Index: 2615153 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.2860. Min Act: -0.1700
Data Index: 4962382 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.2860. Min Act: -0.1700
Data Index: 4887753 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.2860. Min Act: -0.1700
Data Index: 2133962 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.2860. Min Act: -0.1700
Data Index: 3392316 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.2860. Min Act: -0.1700
Data Index: 2785693 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.2548. Min Act: -0.1700
Data Index: 4495311 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.2548. Min Act: -0.1700
Data Index: 4938224 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.2548. Min Act: -0.1700
Data Index: 1138010 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.2548. Min Act: -0.1700
Data Index: 7141792 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9735. Min Range: -4.9735
Max Act: 4.2548. Min Act: -0.1700
Data Index: 3362418 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19