Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1750 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1092. Min Range: -3.1092
Max Act: 3.1092. Min Act: -0.1700
Data Index: 4570309 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1092. Min Range: -3.1092
Max Act: 2.8085. Min Act: -0.1700
Data Index: 7181413 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1092. Min Range: -3.1092
Max Act: 2.8085. Min Act: -0.1700
Data Index: 7169053 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1092. Min Range: -3.1092
Max Act: 2.7766. Min Act: -0.1700
Data Index: 2624525 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1092. Min Range: -3.1092
Max Act: 2.7766. Min Act: -0.1700
Data Index: 7840836 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1092. Min Range: -3.1092
Max Act: 2.7447. Min Act: -0.1700
Data Index: 8721865 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1092. Min Range: -3.1092
Max Act: 2.7607. Min Act: -0.1700
Data Index: 7431260 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1092. Min Range: -3.1092
Max Act: 2.7607. Min Act: -0.1700
Data Index: 1922119 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1092. Min Range: -3.1092
Max Act: 2.7607. Min Act: -0.1700
Data Index: 2833433 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1092. Min Range: -3.1092
Max Act: 2.7287. Min Act: -0.1700
Data Index: 8626258 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1092. Min Range: -3.1092
Max Act: 2.7607. Min Act: -0.1700
Data Index: 1654412 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1092. Min Range: -3.1092
Max Act: 2.7447. Min Act: -0.1700
Data Index: 1222704 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1092. Min Range: -3.1092
Max Act: 2.7447. Min Act: -0.1700
Data Index: 5967810 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1092. Min Range: -3.1092
Max Act: 2.7287. Min Act: -0.1700
Data Index: 8234636 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1092. Min Range: -3.1092
Max Act: 2.7287. Min Act: -0.1700
Data Index: 164540 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1092. Min Range: -3.1092
Max Act: 2.7128. Min Act: -0.1700
Data Index: 4302931 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1092. Min Range: -3.1092
Max Act: 2.7287. Min Act: -0.1700
Data Index: 3478576 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1092. Min Range: -3.1092
Max Act: 2.7128. Min Act: -0.1700
Data Index: 2315128 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1092. Min Range: -3.1092
Max Act: 2.6968. Min Act: -0.1700
Data Index: 6738417 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1092. Min Range: -3.1092
Max Act: 2.7128. Min Act: -0.1700
Data Index: 3717959 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19