Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4988 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5710. Min Range: -7.5710
Max Act: 7.5710. Min Act: -0.1700
Data Index: 1723837 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5710. Min Range: -7.5710
Max Act: 7.5398. Min Act: -0.1700
Data Index: 3878809 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5710. Min Range: -7.5710
Max Act: 7.3210. Min Act: -0.1700
Data Index: 6582178 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5710. Min Range: -7.5710
Max Act: 7.2585. Min Act: -0.1700
Data Index: 4417691 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5710. Min Range: -7.5710
Max Act: 7.2585. Min Act: -0.1700
Data Index: 8067838 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5710. Min Range: -7.5710
Max Act: 7.2273. Min Act: -0.1700
Data Index: 3328847 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5710. Min Range: -7.5710
Max Act: 7.2273. Min Act: -0.1700
Data Index: 547888 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5710. Min Range: -7.5710
Max Act: 7.1960. Min Act: -0.1700
Data Index: 6512239 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5710. Min Range: -7.5710
Max Act: 7.1960. Min Act: -0.1700
Data Index: 1611638 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5710. Min Range: -7.5710
Max Act: 7.1648. Min Act: -0.1700
Data Index: 6721391 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5710. Min Range: -7.5710
Max Act: 7.1648. Min Act: -0.1700
Data Index: 1209327 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5710. Min Range: -7.5710
Max Act: 7.1648. Min Act: -0.1700
Data Index: 3193917 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5710. Min Range: -7.5710
Max Act: 7.1648. Min Act: -0.1700
Data Index: 6857757 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5710. Min Range: -7.5710
Max Act: 7.1648. Min Act: -0.1700
Data Index: 934394 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5710. Min Range: -7.5710
Max Act: 7.1023. Min Act: -0.1700
Data Index: 6674685 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5710. Min Range: -7.5710
Max Act: 7.1023. Min Act: -0.1700
Data Index: 1426212 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5710. Min Range: -7.5710
Max Act: 7.1023. Min Act: -0.1700
Data Index: 6309280 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5710. Min Range: -7.5710
Max Act: 7.0710. Min Act: -0.1700
Data Index: 6910074 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5710. Min Range: -7.5710
Max Act: 7.0710. Min Act: -0.1700
Data Index: 6106168 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5710. Min Range: -7.5710
Max Act: 7.0710. Min Act: -0.1700
Data Index: 7901747 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19