Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2670 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0422. Min Range: -6.0422
Max Act: 6.0422. Min Act: -0.1700
Data Index: 8808091 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0422. Min Range: -6.0422
Max Act: 5.9172. Min Act: -0.1700
Data Index: 2783843 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0422. Min Range: -6.0422
Max Act: 5.8859. Min Act: -0.1700
Data Index: 8541675 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0422. Min Range: -6.0422
Max Act: 5.8859. Min Act: -0.1700
Data Index: 668024 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0422. Min Range: -6.0422
Max Act: 5.8547. Min Act: -0.1700
Data Index: 6828313 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0422. Min Range: -6.0422
Max Act: 5.8547. Min Act: -0.1700
Data Index: 6881195 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0422. Min Range: -6.0422
Max Act: 5.8234. Min Act: -0.1700
Data Index: 4875334 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0422. Min Range: -6.0422
Max Act: 5.8234. Min Act: -0.1700
Data Index: 211296 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0422. Min Range: -6.0422
Max Act: 5.7922. Min Act: -0.1700
Data Index: 6781853 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0422. Min Range: -6.0422
Max Act: 5.7922. Min Act: -0.1700
Data Index: 1186309 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0422. Min Range: -6.0422
Max Act: 5.7609. Min Act: -0.1700
Data Index: 8515415 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0422. Min Range: -6.0422
Max Act: 5.7609. Min Act: -0.1700
Data Index: 457835 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0422. Min Range: -6.0422
Max Act: 5.7609. Min Act: -0.1700
Data Index: 6929731 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0422. Min Range: -6.0422
Max Act: 5.6984. Min Act: -0.1700
Data Index: 2643004 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0422. Min Range: -6.0422
Max Act: 5.7297. Min Act: -0.1700
Data Index: 8317026 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0422. Min Range: -6.0422
Max Act: 5.7609. Min Act: -0.1700
Data Index: 1813077 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0422. Min Range: -6.0422
Max Act: 5.7297. Min Act: -0.1700
Data Index: 6050301 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0422. Min Range: -6.0422
Max Act: 5.7297. Min Act: -0.1700
Data Index: 2141977 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0422. Min Range: -6.0422
Max Act: 5.6984. Min Act: -0.1700
Data Index: 2533787 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0422. Min Range: -6.0422
Max Act: 5.7297. Min Act: -0.1700
Data Index: 5904372 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19