Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3382 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8276. Min Range: -6.8276
Max Act: 6.8276. Min Act: -0.1700
Data Index: 1064146 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8276. Min Range: -6.8276
Max Act: 6.7963. Min Act: -0.1700
Data Index: 1485405 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8276. Min Range: -6.8276
Max Act: 6.6713. Min Act: -0.1700
Data Index: 5329713 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8276. Min Range: -6.8276
Max Act: 6.5463. Min Act: -0.1700
Data Index: 3760663 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8276. Min Range: -6.8276
Max Act: 6.4838. Min Act: -0.1700
Data Index: 5880278 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8276. Min Range: -6.8276
Max Act: 6.3901. Min Act: -0.1700
Data Index: 1497023 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8276. Min Range: -6.8276
Max Act: 6.2963. Min Act: -0.1700
Data Index: 215062 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8276. Min Range: -6.8276
Max Act: 6.2963. Min Act: -0.1700
Data Index: 250385 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8276. Min Range: -6.8276
Max Act: 6.2963. Min Act: -0.1700
Data Index: 2197122 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8276. Min Range: -6.8276
Max Act: 6.2963. Min Act: -0.1700
Data Index: 495366 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8276. Min Range: -6.8276
Max Act: 6.2651. Min Act: -0.1700
Data Index: 4128595 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8276. Min Range: -6.8276
Max Act: 6.2338. Min Act: -0.1700
Data Index: 3288515 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8276. Min Range: -6.8276
Max Act: 6.1401. Min Act: -0.1700
Data Index: 1590375 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8276. Min Range: -6.8276
Max Act: 6.1401. Min Act: -0.1700
Data Index: 8476640 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8276. Min Range: -6.8276
Max Act: 6.1088. Min Act: -0.1700
Data Index: 2667204 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8276. Min Range: -6.8276
Max Act: 6.1088. Min Act: -0.1700
Data Index: 1372175 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8276. Min Range: -6.8276
Max Act: 6.0776. Min Act: -0.1700
Data Index: 3277575 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8276. Min Range: -6.8276
Max Act: 6.0776. Min Act: -0.1700
Data Index: 2787830 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8276. Min Range: -6.8276
Max Act: 6.0463. Min Act: -0.1700
Data Index: 909943 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8276. Min Range: -6.8276
Max Act: 6.0776. Min Act: -0.1700
Data Index: 6369892 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19