Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1895 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0607. Min Range: -5.0607
Max Act: 5.0607. Min Act: -0.1700
Data Index: 1679972 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0607. Min Range: -5.0607
Max Act: 4.9982. Min Act: -0.1700
Data Index: 5848545 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0607. Min Range: -5.0607
Max Act: 4.9670. Min Act: -0.1700
Data Index: 3113887 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0607. Min Range: -5.0607
Max Act: 4.9357. Min Act: -0.1700
Data Index: 1260313 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0607. Min Range: -5.0607
Max Act: 4.9670. Min Act: -0.1700
Data Index: 744689 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0607. Min Range: -5.0607
Max Act: 4.8732. Min Act: -0.1700
Data Index: 4958938 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0607. Min Range: -5.0607
Max Act: 4.8732. Min Act: -0.1700
Data Index: 2765006 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0607. Min Range: -5.0607
Max Act: 4.8732. Min Act: -0.1700
Data Index: 4428880 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0607. Min Range: -5.0607
Max Act: 4.8107. Min Act: -0.1700
Data Index: 8144447 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0607. Min Range: -5.0607
Max Act: 4.8107. Min Act: -0.1700
Data Index: 6526338 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0607. Min Range: -5.0607
Max Act: 4.7482. Min Act: -0.1700
Data Index: 6469676 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0607. Min Range: -5.0607
Max Act: 4.7482. Min Act: -0.1700
Data Index: 2210420 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0607. Min Range: -5.0607
Max Act: 4.7170. Min Act: -0.1700
Data Index: 6619503 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0607. Min Range: -5.0607
Max Act: 4.7170. Min Act: -0.1700
Data Index: 3299290 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0607. Min Range: -5.0607
Max Act: 4.7170. Min Act: -0.1700
Data Index: 5569856 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0607. Min Range: -5.0607
Max Act: 4.7170. Min Act: -0.1700
Data Index: 1149643 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0607. Min Range: -5.0607
Max Act: 4.7170. Min Act: -0.1700
Data Index: 1865044 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0607. Min Range: -5.0607
Max Act: 4.6857. Min Act: -0.1700
Data Index: 6703535 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0607. Min Range: -5.0607
Max Act: 4.6857. Min Act: -0.1700
Data Index: 7776829 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0607. Min Range: -5.0607
Max Act: 4.6545. Min Act: -0.1700
Data Index: 1450074 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19