Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4845 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.4775. Min Act: -0.1700
Data Index: 6754058 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.4462. Min Act: -0.1700
Data Index: 2309371 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.4462. Min Act: -0.1700
Data Index: 6952933 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.4462. Min Act: -0.1700
Data Index: 2538598 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.3678. Min Act: -0.1700
Data Index: 2847852 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.3835. Min Act: -0.1700
Data Index: 8645494 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.3364. Min Act: -0.1700
Data Index: 7472175 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.3364. Min Act: -0.1700
Data Index: 8712111 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.3207. Min Act: -0.1700
Data Index: 7972960 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.2893. Min Act: -0.1700
Data Index: 5088025 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.2736. Min Act: -0.1700
Data Index: 4219701 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.2579. Min Act: -0.1700
Data Index: 5431959 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.2579. Min Act: -0.1700
Data Index: 6127193 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.2579. Min Act: -0.1700
Data Index: 1854565 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.2736. Min Act: -0.1700
Data Index: 486685 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.2422. Min Act: -0.1700
Data Index: 2515643 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.2422. Min Act: -0.1700
Data Index: 4662052 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.2265. Min Act: -0.1700
Data Index: 207771 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.2422. Min Act: -0.1700
Data Index: 5074008 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.2265. Min Act: -0.1700
Data Index: 207769 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19