Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 617 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.4823. Min Act: -0.1700
Data Index: 4104316 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.3885. Min Act: -0.1700
Data Index: 6504041 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.1385. Min Act: -0.1700
Data Index: 4733050 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.1072. Min Act: -0.1700
Data Index: 552598 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.1072. Min Act: -0.1700
Data Index: 4110440 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.1072. Min Act: -0.1700
Data Index: 1454279 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.1072. Min Act: -0.1700
Data Index: 8698965 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.0760. Min Act: -0.1700
Data Index: 4165761 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.0447. Min Act: -0.1700
Data Index: 48601 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.0135. Min Act: -0.1700
Data Index: 4922558 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.0135. Min Act: -0.1700
Data Index: 5488287 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.0135. Min Act: -0.1700
Data Index: 6135371 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.0135. Min Act: -0.1700
Data Index: 59475 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.0135. Min Act: -0.1700
Data Index: 2114352 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4823. Min Range: -4.4823
Max Act: 3.9822. Min Act: -0.1700
Data Index: 2721151 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4823. Min Range: -4.4823
Max Act: 3.9509. Min Act: -0.1700
Data Index: 4907909 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4823. Min Range: -4.4823
Max Act: 3.9197. Min Act: -0.1700
Data Index: 5936823 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4823. Min Range: -4.4823
Max Act: 3.9509. Min Act: -0.1700
Data Index: 5592940 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4823. Min Range: -4.4823
Max Act: 3.9509. Min Act: -0.1700
Data Index: 4022194 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4823. Min Range: -4.4823
Max Act: 3.9197. Min Act: -0.1700
Data Index: 583589 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19