Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4706 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.8638. Min Act: -0.1700
Data Index: 8067118 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.8638. Min Act: -0.1700
Data Index: 2128740 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.6763. Min Act: -0.1700
Data Index: 2160258 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.6138. Min Act: -0.1700
Data Index: 3266750 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.6450. Min Act: -0.1700
Data Index: 2295353 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.5825. Min Act: -0.1700
Data Index: 3710120 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.5825. Min Act: -0.1700
Data Index: 5590360 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.5513. Min Act: -0.1700
Data Index: 1230447 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.5200. Min Act: -0.1700
Data Index: 6426713 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.5200. Min Act: -0.1700
Data Index: 35888 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.4888. Min Act: -0.1700
Data Index: 5435233 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.4888. Min Act: -0.1700
Data Index: 4541845 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.4888. Min Act: -0.1700
Data Index: 135964 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.4888. Min Act: -0.1700
Data Index: 623940 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.4575. Min Act: -0.1700
Data Index: 2265262 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.4888. Min Act: -0.1700
Data Index: 2950214 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.4575. Min Act: -0.1700
Data Index: 3708762 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.4575. Min Act: -0.1700
Data Index: 2755154 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.4575. Min Act: -0.1700
Data Index: 5410018 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.4575. Min Act: -0.1700
Data Index: 7160885 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19