Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4647 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4511. Min Range: -9.4511
Max Act: 9.4511. Min Act: -0.1700
Data Index: 4406424 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4511. Min Range: -9.4511
Max Act: 8.9511. Min Act: -0.1700
Data Index: 1643016 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4511. Min Range: -9.4511
Max Act: 8.7011. Min Act: -0.1700
Data Index: 8451116 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4511. Min Range: -9.4511
Max Act: 8.8261. Min Act: -0.1700
Data Index: 5502258 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4511. Min Range: -9.4511
Max Act: 8.7636. Min Act: -0.1700
Data Index: 2798969 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4511. Min Range: -9.4511
Max Act: 8.7011. Min Act: -0.1700
Data Index: 3918216 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4511. Min Range: -9.4511
Max Act: 8.7011. Min Act: -0.1700
Data Index: 212338 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4511. Min Range: -9.4511
Max Act: 8.6386. Min Act: -0.1700
Data Index: 5708549 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4511. Min Range: -9.4511
Max Act: 8.6386. Min Act: -0.1700
Data Index: 226340 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4511. Min Range: -9.4511
Max Act: 8.5761. Min Act: -0.1700
Data Index: 1090408 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4511. Min Range: -9.4511
Max Act: 8.5761. Min Act: -0.1700
Data Index: 6151939 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4511. Min Range: -9.4511
Max Act: 8.5136. Min Act: -0.1700
Data Index: 8277489 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4511. Min Range: -9.4511
Max Act: 8.5136. Min Act: -0.1700
Data Index: 7347288 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4511. Min Range: -9.4511
Max Act: 8.3886. Min Act: -0.1700
Data Index: 148686 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4511. Min Range: -9.4511
Max Act: 8.3261. Min Act: -0.1700
Data Index: 6343099 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4511. Min Range: -9.4511
Max Act: 8.3886. Min Act: -0.1700
Data Index: 6865999 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4511. Min Range: -9.4511
Max Act: 8.3886. Min Act: -0.1700
Data Index: 5541519 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4511. Min Range: -9.4511
Max Act: 8.3886. Min Act: -0.1700
Data Index: 7580478 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4511. Min Range: -9.4511
Max Act: 8.3261. Min Act: -0.1700
Data Index: 1792374 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4511. Min Range: -9.4511
Max Act: 8.3261. Min Act: -0.1700
Data Index: 2782228 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19