Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4043 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5345. Min Range: -2.5345
Max Act: 2.5345. Min Act: -0.1700
Data Index: 2192276 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5345. Min Range: -2.5345
Max Act: 2.5022. Min Act: -0.1700
Data Index: 7345539 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5345. Min Range: -2.5345
Max Act: 2.4535. Min Act: -0.1700
Data Index: 2813906 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5345. Min Range: -2.5345
Max Act: 2.4209. Min Act: -0.1700
Data Index: 3616787 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5345. Min Range: -2.5345
Max Act: 2.4372. Min Act: -0.1700
Data Index: 7681080 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5345. Min Range: -2.5345
Max Act: 2.4046. Min Act: -0.1700
Data Index: 1357002 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5345. Min Range: -2.5345
Max Act: 2.4209. Min Act: -0.1700
Data Index: 3263034 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5345. Min Range: -2.5345
Max Act: 2.4046. Min Act: -0.1700
Data Index: 7620699 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5345. Min Range: -2.5345
Max Act: 2.4046. Min Act: -0.1700
Data Index: 5070099 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5345. Min Range: -2.5345
Max Act: 2.4046. Min Act: -0.1700
Data Index: 4966968 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5345. Min Range: -2.5345
Max Act: 2.4046. Min Act: -0.1700
Data Index: 3292154 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5345. Min Range: -2.5345
Max Act: 2.3883. Min Act: -0.1700
Data Index: 3667744 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5345. Min Range: -2.5345
Max Act: 2.3883. Min Act: -0.1700
Data Index: 3146983 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5345. Min Range: -2.5345
Max Act: 2.3883. Min Act: -0.1700
Data Index: 5098504 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5345. Min Range: -2.5345
Max Act: 2.3883. Min Act: -0.1700
Data Index: 3203476 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5345. Min Range: -2.5345
Max Act: 2.4046. Min Act: -0.1700
Data Index: 6657434 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5345. Min Range: -2.5345
Max Act: 2.3883. Min Act: -0.1700
Data Index: 2282967 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5345. Min Range: -2.5345
Max Act: 2.3883. Min Act: -0.1700
Data Index: 6069930 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5345. Min Range: -2.5345
Max Act: 2.3720. Min Act: -0.1700
Data Index: 1473199 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5345. Min Range: -2.5345
Max Act: 2.3883. Min Act: -0.1700
Data Index: 6664070 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19