Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2606 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2817. Min Range: -8.2817
Max Act: 8.2817. Min Act: -0.1700
Data Index: 2308859 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2817. Min Range: -8.2817
Max Act: 8.1879. Min Act: -0.1700
Data Index: 4045614 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2817. Min Range: -8.2817
Max Act: 8.0629. Min Act: -0.1700
Data Index: 4045601 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2817. Min Range: -8.2817
Max Act: 7.9067. Min Act: -0.1700
Data Index: 5474838 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2817. Min Range: -8.2817
Max Act: 7.8129. Min Act: -0.1700
Data Index: 5622247 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2817. Min Range: -8.2817
Max Act: 7.8442. Min Act: -0.1700
Data Index: 3712110 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2817. Min Range: -8.2817
Max Act: 7.8129. Min Act: -0.1700
Data Index: 3884830 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2817. Min Range: -8.2817
Max Act: 7.7504. Min Act: -0.1700
Data Index: 4662302 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2817. Min Range: -8.2817
Max Act: 7.7192. Min Act: -0.1700
Data Index: 1336439 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2817. Min Range: -8.2817
Max Act: 7.6567. Min Act: -0.1700
Data Index: 5474817 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2817. Min Range: -8.2817
Max Act: 7.6567. Min Act: -0.1700
Data Index: 5474808 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2817. Min Range: -8.2817
Max Act: 7.6254. Min Act: -0.1700
Data Index: 4108171 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2817. Min Range: -8.2817
Max Act: 7.6254. Min Act: -0.1700
Data Index: 5474842 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2817. Min Range: -8.2817
Max Act: 7.5942. Min Act: -0.1700
Data Index: 2655349 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2817. Min Range: -8.2817
Max Act: 7.6254. Min Act: -0.1700
Data Index: 3105245 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2817. Min Range: -8.2817
Max Act: 7.5629. Min Act: -0.1700
Data Index: 931941 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2817. Min Range: -8.2817
Max Act: 7.5004. Min Act: -0.1700
Data Index: 2655344 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2817. Min Range: -8.2817
Max Act: 7.5004. Min Act: -0.1700
Data Index: 6153532 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2817. Min Range: -8.2817
Max Act: 7.4692. Min Act: -0.1700
Data Index: 5474832 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2817. Min Range: -8.2817
Max Act: 7.5004. Min Act: -0.1700
Data Index: 1826367 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19