Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2353 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9089. Min Range: -5.9089
Max Act: 5.9089. Min Act: -0.1700
Data Index: 4362501 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9089. Min Range: -5.9089
Max Act: 5.7839. Min Act: -0.1700
Data Index: 4571646 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9089. Min Range: -5.9089
Max Act: 5.7839. Min Act: -0.1700
Data Index: 971010 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9089. Min Range: -5.9089
Max Act: 5.7214. Min Act: -0.1700
Data Index: 7983333 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9089. Min Range: -5.9089
Max Act: 5.6589. Min Act: -0.1700
Data Index: 4842678 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9089. Min Range: -5.9089
Max Act: 5.6901. Min Act: -0.1700
Data Index: 5392402 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9089. Min Range: -5.9089
Max Act: 5.7214. Min Act: -0.1700
Data Index: 2852191 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9089. Min Range: -5.9089
Max Act: 5.6901. Min Act: -0.1700
Data Index: 815739 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9089. Min Range: -5.9089
Max Act: 5.6589. Min Act: -0.1700
Data Index: 6693543 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9089. Min Range: -5.9089
Max Act: 5.6276. Min Act: -0.1700
Data Index: 7377637 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9089. Min Range: -5.9089
Max Act: 5.6276. Min Act: -0.1700
Data Index: 6683884 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9089. Min Range: -5.9089
Max Act: 5.6276. Min Act: -0.1700
Data Index: 3150555 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9089. Min Range: -5.9089
Max Act: 5.5964. Min Act: -0.1700
Data Index: 3239123 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9089. Min Range: -5.9089
Max Act: 5.5964. Min Act: -0.1700
Data Index: 2405875 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9089. Min Range: -5.9089
Max Act: 5.5964. Min Act: -0.1700
Data Index: 3452188 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9089. Min Range: -5.9089
Max Act: 5.5651. Min Act: -0.1700
Data Index: 7810184 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9089. Min Range: -5.9089
Max Act: 5.6276. Min Act: -0.1700
Data Index: 4039396 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9089. Min Range: -5.9089
Max Act: 5.5339. Min Act: -0.1700
Data Index: 7767705 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9089. Min Range: -5.9089
Max Act: 5.5651. Min Act: -0.1700
Data Index: 4859947 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9089. Min Range: -5.9089
Max Act: 5.5651. Min Act: -0.1700
Data Index: 7906630 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19