Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3386 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0540. Min Range: -7.0540
Max Act: 7.0540. Min Act: -0.1700
Data Index: 3170106 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0540. Min Range: -7.0540
Max Act: 7.0228. Min Act: -0.1700
Data Index: 2939103 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0540. Min Range: -7.0540
Max Act: 7.0228. Min Act: -0.1700
Data Index: 226838 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0540. Min Range: -7.0540
Max Act: 6.8665. Min Act: -0.1700
Data Index: 1313260 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0540. Min Range: -7.0540
Max Act: 6.8665. Min Act: -0.1700
Data Index: 3959036 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0540. Min Range: -7.0540
Max Act: 6.8353. Min Act: -0.1700
Data Index: 8688438 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0540. Min Range: -7.0540
Max Act: 6.8353. Min Act: -0.1700
Data Index: 2238090 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0540. Min Range: -7.0540
Max Act: 6.8353. Min Act: -0.1700
Data Index: 3534494 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0540. Min Range: -7.0540
Max Act: 6.8040. Min Act: -0.1700
Data Index: 8285777 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0540. Min Range: -7.0540
Max Act: 6.8040. Min Act: -0.1700
Data Index: 4908479 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0540. Min Range: -7.0540
Max Act: 6.8040. Min Act: -0.1700
Data Index: 1614470 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0540. Min Range: -7.0540
Max Act: 6.7728. Min Act: -0.1700
Data Index: 707577 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0540. Min Range: -7.0540
Max Act: 6.7728. Min Act: -0.1700
Data Index: 1958326 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0540. Min Range: -7.0540
Max Act: 6.7728. Min Act: -0.1700
Data Index: 6690652 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0540. Min Range: -7.0540
Max Act: 6.7728. Min Act: -0.1700
Data Index: 1958108 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0540. Min Range: -7.0540
Max Act: 6.7728. Min Act: -0.1700
Data Index: 6183968 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0540. Min Range: -7.0540
Max Act: 6.7415. Min Act: -0.1700
Data Index: 802852 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0540. Min Range: -7.0540
Max Act: 6.7415. Min Act: -0.1700
Data Index: 6578382 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0540. Min Range: -7.0540
Max Act: 6.7728. Min Act: -0.1700
Data Index: 7054232 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0540. Min Range: -7.0540
Max Act: 6.7415. Min Act: -0.1700
Data Index: 6457526 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19