Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1787 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.5450. Min Act: -0.1700
Data Index: 7508921 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.4510. Min Act: -0.1700
Data Index: 123789 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.4354. Min Act: -0.1700
Data Index: 3519481 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.4197. Min Act: -0.1700
Data Index: 1090261 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.3727. Min Act: -0.1700
Data Index: 3931357 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.3413. Min Act: -0.1700
Data Index: 8754740 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.3727. Min Act: -0.1700
Data Index: 6937328 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.3099. Min Act: -0.1700
Data Index: 1100676 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.3413. Min Act: -0.1700
Data Index: 5511611 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.3256. Min Act: -0.1700
Data Index: 2801346 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.2942. Min Act: -0.1700
Data Index: 4287014 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.2942. Min Act: -0.1700
Data Index: 6138168 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.3099. Min Act: -0.1700
Data Index: 2169416 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.3099. Min Act: -0.1700
Data Index: 7937159 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.3099. Min Act: -0.1700
Data Index: 6923348 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.2785. Min Act: -0.1700
Data Index: 7468471 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.2942. Min Act: -0.1700
Data Index: 1600410 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.2785. Min Act: -0.1700
Data Index: 5582758 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.2785. Min Act: -0.1700
Data Index: 6676713 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.2471. Min Act: -0.1700
Data Index: 2699297 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19