Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4034 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0385. Min Range: -6.0385
Max Act: 6.0385. Min Act: -0.1700
Data Index: 6830447 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0385. Min Range: -6.0385
Max Act: 5.7260. Min Act: -0.1700
Data Index: 4451428 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0385. Min Range: -6.0385
Max Act: 5.4760. Min Act: -0.1700
Data Index: 7386663 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0385. Min Range: -6.0385
Max Act: 5.4760. Min Act: -0.1700
Data Index: 1441247 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0385. Min Range: -6.0385
Max Act: 5.4760. Min Act: -0.1700
Data Index: 1242793 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0385. Min Range: -6.0385
Max Act: 5.4760. Min Act: -0.1700
Data Index: 2559626 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0385. Min Range: -6.0385
Max Act: 5.3822. Min Act: -0.1700
Data Index: 6988999 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0385. Min Range: -6.0385
Max Act: 5.3822. Min Act: -0.1700
Data Index: 242680 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0385. Min Range: -6.0385
Max Act: 5.3822. Min Act: -0.1700
Data Index: 7553277 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0385. Min Range: -6.0385
Max Act: 5.3197. Min Act: -0.1700
Data Index: 6369123 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0385. Min Range: -6.0385
Max Act: 5.3197. Min Act: -0.1700
Data Index: 5687023 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0385. Min Range: -6.0385
Max Act: 5.3197. Min Act: -0.1700
Data Index: 2848763 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0385. Min Range: -6.0385
Max Act: 5.2885. Min Act: -0.1700
Data Index: 6248705 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0385. Min Range: -6.0385
Max Act: 5.2885. Min Act: -0.1700
Data Index: 5982560 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0385. Min Range: -6.0385
Max Act: 5.2885. Min Act: -0.1700
Data Index: 5126655 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0385. Min Range: -6.0385
Max Act: 5.2885. Min Act: -0.1700
Data Index: 8122516 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0385. Min Range: -6.0385
Max Act: 5.2885. Min Act: -0.1700
Data Index: 5716444 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0385. Min Range: -6.0385
Max Act: 5.2572. Min Act: -0.1700
Data Index: 881316 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0385. Min Range: -6.0385
Max Act: 5.2885. Min Act: -0.1700
Data Index: 5126663 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0385. Min Range: -6.0385
Max Act: 5.2260. Min Act: -0.1700
Data Index: 3715292 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #19