Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3316 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0408. Min Range: -6.0408
Max Act: 6.0408. Min Act: -0.1700
Data Index: 6308449 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0408. Min Range: -6.0408
Max Act: 6.0408. Min Act: -0.1700
Data Index: 4046753 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.9158. Min Act: -0.1700
Data Index: 5508150 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.8533. Min Act: -0.1700
Data Index: 3934346 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.8220. Min Act: -0.1700
Data Index: 4215131 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.7595. Min Act: -0.1700
Data Index: 7160342 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.7908. Min Act: -0.1700
Data Index: 3928174 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.7595. Min Act: -0.1700
Data Index: 1790651 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.7908. Min Act: -0.1700
Data Index: 5051056 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.7595. Min Act: -0.1700
Data Index: 5589260 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.7283. Min Act: -0.1700
Data Index: 5508142 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.7595. Min Act: -0.1700
Data Index: 2203918 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.7283. Min Act: -0.1700
Data Index: 3361156 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.7283. Min Act: -0.1700
Data Index: 7914464 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.6970. Min Act: -0.1700
Data Index: 8370264 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.6970. Min Act: -0.1700
Data Index: 1699673 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.6970. Min Act: -0.1700
Data Index: 8426967 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.6970. Min Act: -0.1700
Data Index: 3951573 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.7283. Min Act: -0.1700
Data Index: 6783446 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.6970. Min Act: -0.1700
Data Index: 2740482 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19