Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1956 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6360. Min Range: -5.6360
Max Act: 5.6360. Min Act: -0.1700
Data Index: 24541 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6360. Min Range: -5.6360
Max Act: 5.3547. Min Act: -0.1700
Data Index: 8596630 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6360. Min Range: -5.6360
Max Act: 5.3235. Min Act: -0.1700
Data Index: 1118185 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6360. Min Range: -5.6360
Max Act: 5.3235. Min Act: -0.1700
Data Index: 316445 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6360. Min Range: -5.6360
Max Act: 5.2922. Min Act: -0.1700
Data Index: 3957369 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6360. Min Range: -5.6360
Max Act: 5.1672. Min Act: -0.1700
Data Index: 5730070 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6360. Min Range: -5.6360
Max Act: 5.1985. Min Act: -0.1700
Data Index: 4314588 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6360. Min Range: -5.6360
Max Act: 5.1672. Min Act: -0.1700
Data Index: 2369137 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6360. Min Range: -5.6360
Max Act: 5.1360. Min Act: -0.1700
Data Index: 2700544 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6360. Min Range: -5.6360
Max Act: 5.1360. Min Act: -0.1700
Data Index: 6267093 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6360. Min Range: -5.6360
Max Act: 5.0735. Min Act: -0.1700
Data Index: 6846642 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6360. Min Range: -5.6360
Max Act: 5.1047. Min Act: -0.1700
Data Index: 6169689 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6360. Min Range: -5.6360
Max Act: 5.1360. Min Act: -0.1700
Data Index: 3412295 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6360. Min Range: -5.6360
Max Act: 5.1047. Min Act: -0.1700
Data Index: 8239611 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6360. Min Range: -5.6360
Max Act: 5.1047. Min Act: -0.1700
Data Index: 5183126 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6360. Min Range: -5.6360
Max Act: 5.0735. Min Act: -0.1700
Data Index: 287568 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6360. Min Range: -5.6360
Max Act: 5.0422. Min Act: -0.1700
Data Index: 3177905 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6360. Min Range: -5.6360
Max Act: 5.0422. Min Act: -0.1700
Data Index: 230428 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6360. Min Range: -5.6360
Max Act: 5.0422. Min Act: -0.1700
Data Index: 4037386 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6360. Min Range: -5.6360
Max Act: 5.0422. Min Act: -0.1700
Data Index: 7890493 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19