Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 384 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3771. Min Range: -5.3771
Max Act: 5.3771. Min Act: -0.1700
Data Index: 8081947 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3771. Min Range: -5.3771
Max Act: 5.2521. Min Act: -0.1700
Data Index: 6275023 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3771. Min Range: -5.3771
Max Act: 5.2521. Min Act: -0.1700
Data Index: 5334907 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3771. Min Range: -5.3771
Max Act: 5.2208. Min Act: -0.1700
Data Index: 1290317 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3771. Min Range: -5.3771
Max Act: 5.2208. Min Act: -0.1700
Data Index: 1392777 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3771. Min Range: -5.3771
Max Act: 5.2208. Min Act: -0.1700
Data Index: 2374346 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3771. Min Range: -5.3771
Max Act: 5.2208. Min Act: -0.1700
Data Index: 4031224 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3771. Min Range: -5.3771
Max Act: 5.2208. Min Act: -0.1700
Data Index: 8622947 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3771. Min Range: -5.3771
Max Act: 5.2208. Min Act: -0.1700
Data Index: 4593959 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3771. Min Range: -5.3771
Max Act: 5.2208. Min Act: -0.1700
Data Index: 3322131 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3771. Min Range: -5.3771
Max Act: 5.1896. Min Act: -0.1700
Data Index: 6178680 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3771. Min Range: -5.3771
Max Act: 5.1583. Min Act: -0.1700
Data Index: 7503957 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3771. Min Range: -5.3771
Max Act: 5.1583. Min Act: -0.1700
Data Index: 6625445 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3771. Min Range: -5.3771
Max Act: 5.1583. Min Act: -0.1700
Data Index: 4321890 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3771. Min Range: -5.3771
Max Act: 5.1583. Min Act: -0.1700
Data Index: 3952700 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3771. Min Range: -5.3771
Max Act: 5.1583. Min Act: -0.1700
Data Index: 6231187 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3771. Min Range: -5.3771
Max Act: 5.1271. Min Act: -0.1700
Data Index: 503333 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3771. Min Range: -5.3771
Max Act: 5.0958. Min Act: -0.1700
Data Index: 8055071 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3771. Min Range: -5.3771
Max Act: 5.0958. Min Act: -0.1700
Data Index: 8759590 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3771. Min Range: -5.3771
Max Act: 5.0958. Min Act: -0.1700
Data Index: 966037 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19