Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 703 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0069. Min Range: -6.0069
Max Act: 6.0069. Min Act: -0.1700
Data Index: 4775025 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0069. Min Range: -6.0069
Max Act: 5.9132. Min Act: -0.1700
Data Index: 3846440 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0069. Min Range: -6.0069
Max Act: 5.9132. Min Act: -0.1700
Data Index: 8016265 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0069. Min Range: -6.0069
Max Act: 5.8507. Min Act: -0.1700
Data Index: 8639980 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0069. Min Range: -6.0069
Max Act: 5.8194. Min Act: -0.1700
Data Index: 8288085 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0069. Min Range: -6.0069
Max Act: 5.8194. Min Act: -0.1700
Data Index: 4927228 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0069. Min Range: -6.0069
Max Act: 5.8194. Min Act: -0.1700
Data Index: 3458021 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0069. Min Range: -6.0069
Max Act: 5.8194. Min Act: -0.1700
Data Index: 6738053 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0069. Min Range: -6.0069
Max Act: 5.7569. Min Act: -0.1700
Data Index: 8055887 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0069. Min Range: -6.0069
Max Act: 5.6944. Min Act: -0.1700
Data Index: 1287095 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0069. Min Range: -6.0069
Max Act: 5.7257. Min Act: -0.1700
Data Index: 2920523 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0069. Min Range: -6.0069
Max Act: 5.6632. Min Act: -0.1700
Data Index: 6738055 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0069. Min Range: -6.0069
Max Act: 5.6632. Min Act: -0.1700
Data Index: 5157949 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0069. Min Range: -6.0069
Max Act: 5.6632. Min Act: -0.1700
Data Index: 1312802 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0069. Min Range: -6.0069
Max Act: 5.6944. Min Act: -0.1700
Data Index: 4613163 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0069. Min Range: -6.0069
Max Act: 5.6632. Min Act: -0.1700
Data Index: 2130359 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0069. Min Range: -6.0069
Max Act: 5.6632. Min Act: -0.1700
Data Index: 1936632 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0069. Min Range: -6.0069
Max Act: 5.6319. Min Act: -0.1700
Data Index: 137950 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0069. Min Range: -6.0069
Max Act: 5.6319. Min Act: -0.1700
Data Index: 7514040 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0069. Min Range: -6.0069
Max Act: 5.6007. Min Act: -0.1700
Data Index: 3115347 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19