Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3181 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5401. Min Range: -6.5401
Max Act: 6.5401. Min Act: -0.1700
Data Index: 6057441 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5401. Min Range: -6.5401
Max Act: 6.2901. Min Act: -0.1700
Data Index: 2291424 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5401. Min Range: -6.5401
Max Act: 6.2589. Min Act: -0.1700
Data Index: 8698039 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5401. Min Range: -6.5401
Max Act: 6.2589. Min Act: -0.1700
Data Index: 607852 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5401. Min Range: -6.5401
Max Act: 6.2589. Min Act: -0.1700
Data Index: 5189027 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5401. Min Range: -6.5401
Max Act: 6.1964. Min Act: -0.1700
Data Index: 476938 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5401. Min Range: -6.5401
Max Act: 6.1964. Min Act: -0.1700
Data Index: 6728244 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5401. Min Range: -6.5401
Max Act: 6.1651. Min Act: -0.1700
Data Index: 1981734 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5401. Min Range: -6.5401
Max Act: 6.1651. Min Act: -0.1700
Data Index: 6229835 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5401. Min Range: -6.5401
Max Act: 6.1026. Min Act: -0.1700
Data Index: 8750597 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5401. Min Range: -6.5401
Max Act: 6.1026. Min Act: -0.1700
Data Index: 5875764 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5401. Min Range: -6.5401
Max Act: 6.1026. Min Act: -0.1700
Data Index: 1529810 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5401. Min Range: -6.5401
Max Act: 6.1026. Min Act: -0.1700
Data Index: 4513291 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5401. Min Range: -6.5401
Max Act: 6.1026. Min Act: -0.1700
Data Index: 303633 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5401. Min Range: -6.5401
Max Act: 6.0714. Min Act: -0.1700
Data Index: 7363249 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5401. Min Range: -6.5401
Max Act: 6.0401. Min Act: -0.1700
Data Index: 251484 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5401. Min Range: -6.5401
Max Act: 6.0089. Min Act: -0.1700
Data Index: 5326956 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5401. Min Range: -6.5401
Max Act: 6.0401. Min Act: -0.1700
Data Index: 4247897 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5401. Min Range: -6.5401
Max Act: 6.0401. Min Act: -0.1700
Data Index: 5011927 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5401. Min Range: -6.5401
Max Act: 6.0401. Min Act: -0.1700
Data Index: 2150707 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19