Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3106 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3169. Min Range: -7.3169
Max Act: 7.3169. Min Act: -0.1700
Data Index: 8042025 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3169. Min Range: -7.3169
Max Act: 7.2544. Min Act: -0.1700
Data Index: 361297 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3169. Min Range: -7.3169
Max Act: 7.2232. Min Act: -0.1700
Data Index: 5765706 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3169. Min Range: -7.3169
Max Act: 7.1294. Min Act: -0.1700
Data Index: 644182 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3169. Min Range: -7.3169
Max Act: 7.1607. Min Act: -0.1700
Data Index: 3037683 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3169. Min Range: -7.3169
Max Act: 7.0982. Min Act: -0.1700
Data Index: 7881699 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3169. Min Range: -7.3169
Max Act: 7.0357. Min Act: -0.1700
Data Index: 3939996 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3169. Min Range: -7.3169
Max Act: 7.0044. Min Act: -0.1700
Data Index: 7538417 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3169. Min Range: -7.3169
Max Act: 7.0044. Min Act: -0.1700
Data Index: 6571112 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3169. Min Range: -7.3169
Max Act: 6.9732. Min Act: -0.1700
Data Index: 934573 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3169. Min Range: -7.3169
Max Act: 6.9107. Min Act: -0.1700
Data Index: 6136112 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3169. Min Range: -7.3169
Max Act: 6.8482. Min Act: -0.1700
Data Index: 4455699 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3169. Min Range: -7.3169
Max Act: 6.8482. Min Act: -0.1700
Data Index: 5032383 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3169. Min Range: -7.3169
Max Act: 6.7857. Min Act: -0.1700
Data Index: 2761143 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3169. Min Range: -7.3169
Max Act: 6.7857. Min Act: -0.1700
Data Index: 4950961 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3169. Min Range: -7.3169
Max Act: 6.7857. Min Act: -0.1700
Data Index: 4952055 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3169. Min Range: -7.3169
Max Act: 6.7232. Min Act: -0.1700
Data Index: 2907920 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3169. Min Range: -7.3169
Max Act: 6.7232. Min Act: -0.1700
Data Index: 3379925 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3169. Min Range: -7.3169
Max Act: 6.7544. Min Act: -0.1700
Data Index: 2607366 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3169. Min Range: -7.3169
Max Act: 6.7232. Min Act: -0.1700
Data Index: 4198389 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19