Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3170 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5450. Min Range: -6.5450
Max Act: 6.5450. Min Act: -0.1700
Data Index: 1835691 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5450. Min Range: -6.5450
Max Act: 6.2013. Min Act: -0.1700
Data Index: 8158857 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5450. Min Range: -6.5450
Max Act: 6.0763. Min Act: -0.1700
Data Index: 5003890 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5450. Min Range: -6.5450
Max Act: 6.0138. Min Act: -0.1700
Data Index: 2056883 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5450. Min Range: -6.5450
Max Act: 5.9513. Min Act: -0.1700
Data Index: 6104794 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5450. Min Range: -6.5450
Max Act: 5.9513. Min Act: -0.1700
Data Index: 7319244 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5450. Min Range: -6.5450
Max Act: 5.9825. Min Act: -0.1700
Data Index: 2694731 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5450. Min Range: -6.5450
Max Act: 5.9200. Min Act: -0.1700
Data Index: 4333860 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5450. Min Range: -6.5450
Max Act: 5.9200. Min Act: -0.1700
Data Index: 4606775 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5450. Min Range: -6.5450
Max Act: 5.9200. Min Act: -0.1700
Data Index: 4012912 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5450. Min Range: -6.5450
Max Act: 5.8888. Min Act: -0.1700
Data Index: 8251908 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5450. Min Range: -6.5450
Max Act: 5.8888. Min Act: -0.1700
Data Index: 1978064 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5450. Min Range: -6.5450
Max Act: 5.8888. Min Act: -0.1700
Data Index: 132962 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5450. Min Range: -6.5450
Max Act: 5.8263. Min Act: -0.1700
Data Index: 3574557 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5450. Min Range: -6.5450
Max Act: 5.8575. Min Act: -0.1700
Data Index: 4752363 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5450. Min Range: -6.5450
Max Act: 5.8575. Min Act: -0.1700
Data Index: 7022671 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5450. Min Range: -6.5450
Max Act: 5.8575. Min Act: -0.1700
Data Index: 6725128 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5450. Min Range: -6.5450
Max Act: 5.8575. Min Act: -0.1700
Data Index: 101993 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5450. Min Range: -6.5450
Max Act: 5.8263. Min Act: -0.1700
Data Index: 5754052 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5450. Min Range: -6.5450
Max Act: 5.7950. Min Act: -0.1700
Data Index: 7586947 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19