Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5700 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7280. Min Range: -7.7280
Max Act: 7.7280. Min Act: -0.1700
Data Index: 4677058 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7280. Min Range: -7.7280
Max Act: 7.6655. Min Act: -0.1700
Data Index: 6213635 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7280. Min Range: -7.7280
Max Act: 7.4155. Min Act: -0.1700
Data Index: 8042617 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7280. Min Range: -7.7280
Max Act: 7.4155. Min Act: -0.1700
Data Index: 6636356 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7280. Min Range: -7.7280
Max Act: 7.3842. Min Act: -0.1700
Data Index: 8198379 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7280. Min Range: -7.7280
Max Act: 7.3842. Min Act: -0.1700
Data Index: 3097993 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7280. Min Range: -7.7280
Max Act: 7.3530. Min Act: -0.1700
Data Index: 4247493 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7280. Min Range: -7.7280
Max Act: 7.2592. Min Act: -0.1700
Data Index: 8333902 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7280. Min Range: -7.7280
Max Act: 7.2592. Min Act: -0.1700
Data Index: 7732400 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7280. Min Range: -7.7280
Max Act: 7.2280. Min Act: -0.1700
Data Index: 508232 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7280. Min Range: -7.7280
Max Act: 7.1967. Min Act: -0.1700
Data Index: 7534907 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7280. Min Range: -7.7280
Max Act: 7.1967. Min Act: -0.1700
Data Index: 1163147 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7280. Min Range: -7.7280
Max Act: 7.1967. Min Act: -0.1700
Data Index: 5747737 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7280. Min Range: -7.7280
Max Act: 7.1967. Min Act: -0.1700
Data Index: 4073397 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7280. Min Range: -7.7280
Max Act: 7.1655. Min Act: -0.1700
Data Index: 2703367 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7280. Min Range: -7.7280
Max Act: 7.1655. Min Act: -0.1700
Data Index: 880091 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7280. Min Range: -7.7280
Max Act: 7.1655. Min Act: -0.1700
Data Index: 5146950 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7280. Min Range: -7.7280
Max Act: 7.1342. Min Act: -0.1700
Data Index: 1795042 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7280. Min Range: -7.7280
Max Act: 7.1342. Min Act: -0.1700
Data Index: 2168443 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7280. Min Range: -7.7280
Max Act: 7.1342. Min Act: -0.1700
Data Index: 5448316 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19