Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3698 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9521. Min Range: -5.9521
Max Act: 5.9521. Min Act: -0.1700
Data Index: 8424915 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9521. Min Range: -5.9521
Max Act: 5.5458. Min Act: -0.1700
Data Index: 1150524 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9521. Min Range: -5.9521
Max Act: 5.4521. Min Act: -0.1700
Data Index: 243057 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9521. Min Range: -5.9521
Max Act: 5.4208. Min Act: -0.1700
Data Index: 8424916 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9521. Min Range: -5.9521
Max Act: 5.3583. Min Act: -0.1700
Data Index: 4175441 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9521. Min Range: -5.9521
Max Act: 5.3896. Min Act: -0.1700
Data Index: 6645495 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9521. Min Range: -5.9521
Max Act: 5.3583. Min Act: -0.1700
Data Index: 2198392 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9521. Min Range: -5.9521
Max Act: 5.3583. Min Act: -0.1700
Data Index: 8206469 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9521. Min Range: -5.9521
Max Act: 5.3271. Min Act: -0.1700
Data Index: 3339778 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9521. Min Range: -5.9521
Max Act: 5.3271. Min Act: -0.1700
Data Index: 1667248 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9521. Min Range: -5.9521
Max Act: 5.3271. Min Act: -0.1700
Data Index: 8014019 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9521. Min Range: -5.9521
Max Act: 5.3271. Min Act: -0.1700
Data Index: 2501174 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9521. Min Range: -5.9521
Max Act: 5.2958. Min Act: -0.1700
Data Index: 2355204 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9521. Min Range: -5.9521
Max Act: 5.2958. Min Act: -0.1700
Data Index: 439855 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9521. Min Range: -5.9521
Max Act: 5.2646. Min Act: -0.1700
Data Index: 6245790 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9521. Min Range: -5.9521
Max Act: 5.2646. Min Act: -0.1700
Data Index: 8039650 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9521. Min Range: -5.9521
Max Act: 5.2646. Min Act: -0.1700
Data Index: 1294981 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9521. Min Range: -5.9521
Max Act: 5.2333. Min Act: -0.1700
Data Index: 5228195 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9521. Min Range: -5.9521
Max Act: 5.2333. Min Act: -0.1700
Data Index: 8214196 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9521. Min Range: -5.9521
Max Act: 5.2333. Min Act: -0.1700
Data Index: 2301336 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19