Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2079 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8387. Min Range: -7.8387
Max Act: 7.8387. Min Act: -0.1700
Data Index: 7069318 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8387. Min Range: -7.8387
Max Act: 7.6512. Min Act: -0.1700
Data Index: 2399789 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8387. Min Range: -7.8387
Max Act: 7.5574. Min Act: -0.1700
Data Index: 2666390 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8387. Min Range: -7.8387
Max Act: 7.3699. Min Act: -0.1700
Data Index: 2106378 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8387. Min Range: -7.8387
Max Act: 7.3074. Min Act: -0.1700
Data Index: 1082790 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8387. Min Range: -7.8387
Max Act: 7.2449. Min Act: -0.1700
Data Index: 296286 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8387. Min Range: -7.8387
Max Act: 7.2449. Min Act: -0.1700
Data Index: 7129002 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8387. Min Range: -7.8387
Max Act: 7.2449. Min Act: -0.1700
Data Index: 3227709 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8387. Min Range: -7.8387
Max Act: 7.2137. Min Act: -0.1700
Data Index: 3391687 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8387. Min Range: -7.8387
Max Act: 7.1512. Min Act: -0.1700
Data Index: 7173837 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8387. Min Range: -7.8387
Max Act: 7.1512. Min Act: -0.1700
Data Index: 2828745 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8387. Min Range: -7.8387
Max Act: 7.1512. Min Act: -0.1700
Data Index: 7480713 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8387. Min Range: -7.8387
Max Act: 7.1512. Min Act: -0.1700
Data Index: 5959641 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8387. Min Range: -7.8387
Max Act: 7.1512. Min Act: -0.1700
Data Index: 923923 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8387. Min Range: -7.8387
Max Act: 7.0887. Min Act: -0.1700
Data Index: 1683474 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8387. Min Range: -7.8387
Max Act: 7.1512. Min Act: -0.1700
Data Index: 4521352 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8387. Min Range: -7.8387
Max Act: 7.0887. Min Act: -0.1700
Data Index: 8686306 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8387. Min Range: -7.8387
Max Act: 7.0887. Min Act: -0.1700
Data Index: 4734493 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8387. Min Range: -7.8387
Max Act: 7.0574. Min Act: -0.1700
Data Index: 6339638 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8387. Min Range: -7.8387
Max Act: 7.0574. Min Act: -0.1700
Data Index: 1804840 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19