Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3188 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1526. Min Range: -7.1526
Max Act: 7.1526. Min Act: -0.1700
Data Index: 6659576 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1526. Min Range: -7.1526
Max Act: 7.1214. Min Act: -0.1700
Data Index: 6659575 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1526. Min Range: -7.1526
Max Act: 6.9651. Min Act: -0.1700
Data Index: 6659577 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1526. Min Range: -7.1526
Max Act: 6.3089. Min Act: -0.1700
Data Index: 6659578 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1526. Min Range: -7.1526
Max Act: 6.0589. Min Act: -0.1700
Data Index: 2811842 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1526. Min Range: -7.1526
Max Act: 5.9651. Min Act: -0.1700
Data Index: 7839421 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1526. Min Range: -7.1526
Max Act: 5.9339. Min Act: -0.1700
Data Index: 5370905 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1526. Min Range: -7.1526
Max Act: 5.9339. Min Act: -0.1700
Data Index: 6663217 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1526. Min Range: -7.1526
Max Act: 5.9026. Min Act: -0.1700
Data Index: 6781640 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1526. Min Range: -7.1526
Max Act: 5.9026. Min Act: -0.1700
Data Index: 8113116 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1526. Min Range: -7.1526
Max Act: 5.9026. Min Act: -0.1700
Data Index: 3749282 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1526. Min Range: -7.1526
Max Act: 5.9026. Min Act: -0.1700
Data Index: 1390908 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1526. Min Range: -7.1526
Max Act: 5.8401. Min Act: -0.1700
Data Index: 6149899 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1526. Min Range: -7.1526
Max Act: 5.8089. Min Act: -0.1700
Data Index: 2787107 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1526. Min Range: -7.1526
Max Act: 5.8089. Min Act: -0.1700
Data Index: 8429631 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1526. Min Range: -7.1526
Max Act: 5.7776. Min Act: -0.1700
Data Index: 7865604 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1526. Min Range: -7.1526
Max Act: 5.7464. Min Act: -0.1700
Data Index: 6886467 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1526. Min Range: -7.1526
Max Act: 5.7776. Min Act: -0.1700
Data Index: 6563210 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1526. Min Range: -7.1526
Max Act: 5.7151. Min Act: -0.1700
Data Index: 5880613 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1526. Min Range: -7.1526
Max Act: 5.7151. Min Act: -0.1700
Data Index: 6549404 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19