Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2719 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.6694. Min Range: -1.6694
Max Act: 1.6694. Min Act: -0.1700
Data Index: 815836 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6694. Min Range: -1.6694
Max Act: 1.6694. Min Act: -0.1700
Data Index: 1385760 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6694. Min Range: -1.6694
Max Act: 1.6520. Min Act: -0.1700
Data Index: 2900892 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6694. Min Range: -1.6694
Max Act: 1.5997. Min Act: -0.1700
Data Index: 4365762 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6694. Min Range: -1.6694
Max Act: 1.6171. Min Act: -0.1700
Data Index: 1488454 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6694. Min Range: -1.6694
Max Act: 1.5822. Min Act: -0.1700
Data Index: 4509353 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6694. Min Range: -1.6694
Max Act: 1.5647. Min Act: -0.1700
Data Index: 3265798 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6694. Min Range: -1.6694
Max Act: 1.5472. Min Act: -0.1700
Data Index: 5248064 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6694. Min Range: -1.6694
Max Act: 1.5472. Min Act: -0.1700
Data Index: 276904 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6694. Min Range: -1.6694
Max Act: 1.5472. Min Act: -0.1700
Data Index: 5040835 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6694. Min Range: -1.6694
Max Act: 1.5297. Min Act: -0.1700
Data Index: 2249449 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6694. Min Range: -1.6694
Max Act: 1.5472. Min Act: -0.1700
Data Index: 6965624 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6694. Min Range: -1.6694
Max Act: 1.5297. Min Act: -0.1700
Data Index: 3645414 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6694. Min Range: -1.6694
Max Act: 1.5472. Min Act: -0.1700
Data Index: 2633361 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6694. Min Range: -1.6694
Max Act: 1.5472. Min Act: -0.1699
Data Index: 5694236 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6694. Min Range: -1.6694
Max Act: 1.5472. Min Act: -0.1700
Data Index: 7968636 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6694. Min Range: -1.6694
Max Act: 1.5472. Min Act: -0.1700
Data Index: 7952637 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6694. Min Range: -1.6694
Max Act: 1.5121. Min Act: -0.1700
Data Index: 5709554 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6694. Min Range: -1.6694
Max Act: 1.5297. Min Act: -0.1700
Data Index: 1186831 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6694. Min Range: -1.6694
Max Act: 1.5472. Min Act: -0.1700
Data Index: 7308692 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19