Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3020 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4109. Min Range: -5.4109
Max Act: 5.4109. Min Act: -0.1700
Data Index: 7324162 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4109. Min Range: -5.4109
Max Act: 5.4109. Min Act: -0.1700
Data Index: 149142 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4109. Min Range: -5.4109
Max Act: 5.3172. Min Act: -0.1700
Data Index: 1244483 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4109. Min Range: -5.4109
Max Act: 5.3172. Min Act: -0.1700
Data Index: 952429 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4109. Min Range: -5.4109
Max Act: 5.3172. Min Act: -0.1700
Data Index: 3369500 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4109. Min Range: -5.4109
Max Act: 5.2859. Min Act: -0.1700
Data Index: 440824 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4109. Min Range: -5.4109
Max Act: 5.2859. Min Act: -0.1700
Data Index: 8109603 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4109. Min Range: -5.4109
Max Act: 5.2859. Min Act: -0.1700
Data Index: 5764521 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4109. Min Range: -5.4109
Max Act: 5.2859. Min Act: -0.1700
Data Index: 6368464 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4109. Min Range: -5.4109
Max Act: 5.2859. Min Act: -0.1700
Data Index: 2073423 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4109. Min Range: -5.4109
Max Act: 5.2547. Min Act: -0.1700
Data Index: 5583544 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4109. Min Range: -5.4109
Max Act: 5.2547. Min Act: -0.1700
Data Index: 7770899 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4109. Min Range: -5.4109
Max Act: 5.2547. Min Act: -0.1700
Data Index: 4977934 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4109. Min Range: -5.4109
Max Act: 5.2547. Min Act: -0.1700
Data Index: 5138990 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4109. Min Range: -5.4109
Max Act: 5.2234. Min Act: -0.1700
Data Index: 7765531 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4109. Min Range: -5.4109
Max Act: 5.2234. Min Act: -0.1700
Data Index: 4382779 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4109. Min Range: -5.4109
Max Act: 5.2234. Min Act: -0.1700
Data Index: 1137647 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4109. Min Range: -5.4109
Max Act: 5.1922. Min Act: -0.1700
Data Index: 791218 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4109. Min Range: -5.4109
Max Act: 5.2234. Min Act: -0.1700
Data Index: 5663811 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4109. Min Range: -5.4109
Max Act: 5.1922. Min Act: -0.1700
Data Index: 5299553 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19