Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3724 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.3605. Min Act: -0.1700
Data Index: 4441615 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.3292. Min Act: -0.1700
Data Index: 6135672 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.1417. Min Act: -0.1700
Data Index: 4724626 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.1417. Min Act: -0.1700
Data Index: 195644 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.1105. Min Act: -0.1700
Data Index: 6473297 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.1105. Min Act: -0.1700
Data Index: 3019874 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.1105. Min Act: -0.1700
Data Index: 6078700 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.0480. Min Act: -0.1700
Data Index: 925551 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.0480. Min Act: -0.1700
Data Index: 2979465 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3605. Min Range: -5.3605
Max Act: 5.0167. Min Act: -0.1700
Data Index: 8651898 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3605. Min Range: -5.3605
Max Act: 4.9855. Min Act: -0.1700
Data Index: 7127075 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3605. Min Range: -5.3605
Max Act: 4.9855. Min Act: -0.1700
Data Index: 8544590 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3605. Min Range: -5.3605
Max Act: 4.9542. Min Act: -0.1700
Data Index: 947525 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3605. Min Range: -5.3605
Max Act: 4.9542. Min Act: -0.1700
Data Index: 1704580 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3605. Min Range: -5.3605
Max Act: 4.9230. Min Act: -0.1700
Data Index: 6009915 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3605. Min Range: -5.3605
Max Act: 4.8917. Min Act: -0.1700
Data Index: 4790517 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3605. Min Range: -5.3605
Max Act: 4.8917. Min Act: -0.1700
Data Index: 5404526 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3605. Min Range: -5.3605
Max Act: 4.8917. Min Act: -0.1700
Data Index: 3617644 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3605. Min Range: -5.3605
Max Act: 4.8917. Min Act: -0.1700
Data Index: 4468364 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3605. Min Range: -5.3605
Max Act: 4.8917. Min Act: -0.1700
Data Index: 6742343 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19