Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2922 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7987. Min Range: -6.7987
Max Act: 6.7987. Min Act: -0.1700
Data Index: 6256214 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7987. Min Range: -6.7987
Max Act: 6.5174. Min Act: -0.1700
Data Index: 4843799 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7987. Min Range: -6.7987
Max Act: 6.2674. Min Act: -0.1700
Data Index: 4074277 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7987. Min Range: -6.7987
Max Act: 6.1112. Min Act: -0.1700
Data Index: 7892582 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7987. Min Range: -6.7987
Max Act: 6.0799. Min Act: -0.1700
Data Index: 5327406 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7987. Min Range: -6.7987
Max Act: 6.0799. Min Act: -0.1700
Data Index: 4349598 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7987. Min Range: -6.7987
Max Act: 6.0799. Min Act: -0.1700
Data Index: 3185421 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7987. Min Range: -6.7987
Max Act: 6.0174. Min Act: -0.1700
Data Index: 7261320 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7987. Min Range: -6.7987
Max Act: 5.9862. Min Act: -0.1700
Data Index: 7761243 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7987. Min Range: -6.7987
Max Act: 5.9862. Min Act: -0.1700
Data Index: 1412432 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7987. Min Range: -6.7987
Max Act: 5.9862. Min Act: -0.1700
Data Index: 4953731 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7987. Min Range: -6.7987
Max Act: 5.9862. Min Act: -0.1700
Data Index: 4896943 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7987. Min Range: -6.7987
Max Act: 5.9862. Min Act: -0.1700
Data Index: 4055292 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7987. Min Range: -6.7987
Max Act: 5.9549. Min Act: -0.1700
Data Index: 7350171 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7987. Min Range: -6.7987
Max Act: 5.9549. Min Act: -0.1700
Data Index: 7878480 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7987. Min Range: -6.7987
Max Act: 5.9237. Min Act: -0.1700
Data Index: 6390994 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7987. Min Range: -6.7987
Max Act: 5.9549. Min Act: -0.1700
Data Index: 8270947 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7987. Min Range: -6.7987
Max Act: 5.9549. Min Act: -0.1700
Data Index: 2482563 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7987. Min Range: -6.7987
Max Act: 5.9237. Min Act: -0.1700
Data Index: 7149407 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7987. Min Range: -6.7987
Max Act: 5.9237. Min Act: -0.1700
Data Index: 5581549 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19