Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1465 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9652. Min Range: -2.9652
Max Act: 2.9652. Min Act: -0.1700
Data Index: 1324172 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9652. Min Range: -2.9652
Max Act: 2.8860. Min Act: -0.1700
Data Index: 7866644 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9652. Min Range: -2.9652
Max Act: 2.7906. Min Act: -0.1700
Data Index: 3432959 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9652. Min Range: -2.9652
Max Act: 2.7587. Min Act: -0.1700
Data Index: 1324166 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9652. Min Range: -2.9652
Max Act: 2.7587. Min Act: -0.1700
Data Index: 4658580 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9652. Min Range: -2.9652
Max Act: 2.7587. Min Act: -0.1700
Data Index: 6468601 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9652. Min Range: -2.9652
Max Act: 2.7108. Min Act: -0.1700
Data Index: 7119457 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9652. Min Range: -2.9652
Max Act: 2.7268. Min Act: -0.1700
Data Index: 697285 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9652. Min Range: -2.9652
Max Act: 2.7108. Min Act: -0.1700
Data Index: 138802 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9652. Min Range: -2.9652
Max Act: 2.6788. Min Act: -0.1700
Data Index: 829310 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9652. Min Range: -2.9652
Max Act: 2.6788. Min Act: -0.1700
Data Index: 1786517 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9652. Min Range: -2.9652
Max Act: 2.6948. Min Act: -0.1700
Data Index: 3305144 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9652. Min Range: -2.9652
Max Act: 2.7108. Min Act: -0.1700
Data Index: 1000802 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9652. Min Range: -2.9652
Max Act: 2.6948. Min Act: -0.1700
Data Index: 1474467 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9652. Min Range: -2.9652
Max Act: 2.6628. Min Act: -0.1700
Data Index: 3342396 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9652. Min Range: -2.9652
Max Act: 2.6467. Min Act: -0.1700
Data Index: 862984 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9652. Min Range: -2.9652
Max Act: 2.6628. Min Act: -0.1700
Data Index: 2480076 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9652. Min Range: -2.9652
Max Act: 2.6628. Min Act: -0.1700
Data Index: 2736013 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9652. Min Range: -2.9652
Max Act: 2.6467. Min Act: -0.1700
Data Index: 4465345 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9652. Min Range: -2.9652
Max Act: 2.6628. Min Act: -0.1700
Data Index: 5549375 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19