Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 754 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.8884. Min Act: -0.1700
Data Index: 5069802 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.8259. Min Act: -0.1700
Data Index: 4343918 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.7946. Min Act: -0.1700
Data Index: 7461911 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.7946. Min Act: -0.1700
Data Index: 6246068 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.7009. Min Act: -0.1700
Data Index: 7987269 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.7009. Min Act: -0.1700
Data Index: 3561949 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.6696. Min Act: -0.1700
Data Index: 3067963 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.6384. Min Act: -0.1700
Data Index: 199947 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.6384. Min Act: -0.1700
Data Index: 3795934 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.6696. Min Act: -0.1700
Data Index: 4564252 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.6071. Min Act: -0.1700
Data Index: 3300624 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.5759. Min Act: -0.1700
Data Index: 2330937 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.5759. Min Act: -0.1700
Data Index: 3524936 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.5759. Min Act: -0.1700
Data Index: 5069183 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.5759. Min Act: -0.1700
Data Index: 2270496 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.5134. Min Act: -0.1700
Data Index: 7994161 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.5446. Min Act: -0.1700
Data Index: 554305 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.5446. Min Act: -0.1700
Data Index: 5823832 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.5134. Min Act: -0.1700
Data Index: 3343929 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8884. Min Range: -7.8884
Max Act: 7.5134. Min Act: -0.1700
Data Index: 2047685 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19