Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2172 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0432. Min Range: -5.0432
Max Act: 5.0432. Min Act: -0.1700
Data Index: 5918934 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0432. Min Range: -5.0432
Max Act: 5.0119. Min Act: -0.1700
Data Index: 6162934 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0432. Min Range: -5.0432
Max Act: 4.9494. Min Act: -0.1700
Data Index: 6782626 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0432. Min Range: -5.0432
Max Act: 4.9807. Min Act: -0.1700
Data Index: 4289003 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0432. Min Range: -5.0432
Max Act: 4.9494. Min Act: -0.1700
Data Index: 1610434 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0432. Min Range: -5.0432
Max Act: 4.9494. Min Act: -0.1700
Data Index: 2317038 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0432. Min Range: -5.0432
Max Act: 4.9182. Min Act: -0.1700
Data Index: 2732893 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0432. Min Range: -5.0432
Max Act: 4.9182. Min Act: -0.1700
Data Index: 4212029 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0432. Min Range: -5.0432
Max Act: 4.8869. Min Act: -0.1700
Data Index: 4144928 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0432. Min Range: -5.0432
Max Act: 4.8869. Min Act: -0.1700
Data Index: 3524039 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0432. Min Range: -5.0432
Max Act: 4.8557. Min Act: -0.1700
Data Index: 994959 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0432. Min Range: -5.0432
Max Act: 4.8244. Min Act: -0.1700
Data Index: 7453690 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0432. Min Range: -5.0432
Max Act: 4.8557. Min Act: -0.1700
Data Index: 7906767 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0432. Min Range: -5.0432
Max Act: 4.8244. Min Act: -0.1700
Data Index: 6149358 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0432. Min Range: -5.0432
Max Act: 4.7932. Min Act: -0.1700
Data Index: 3625249 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0432. Min Range: -5.0432
Max Act: 4.8244. Min Act: -0.1700
Data Index: 507915 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0432. Min Range: -5.0432
Max Act: 4.8557. Min Act: -0.1700
Data Index: 1659022 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0432. Min Range: -5.0432
Max Act: 4.8244. Min Act: -0.1700
Data Index: 6590689 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0432. Min Range: -5.0432
Max Act: 4.8244. Min Act: -0.1700
Data Index: 5396677 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0432. Min Range: -5.0432
Max Act: 4.8244. Min Act: -0.1700
Data Index: 1980440 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19