Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1351 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5547. Min Range: -2.5547
Max Act: 2.5547. Min Act: -0.1700
Data Index: 5066981 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5547. Min Range: -2.5547
Max Act: 2.3924. Min Act: -0.1700
Data Index: 4661594 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5547. Min Range: -2.5547
Max Act: 2.3433. Min Act: -0.1700
Data Index: 6136978 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5547. Min Range: -2.5547
Max Act: 2.3269. Min Act: -0.1700
Data Index: 2428228 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5547. Min Range: -2.5547
Max Act: 2.3105. Min Act: -0.1700
Data Index: 934274 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5547. Min Range: -2.5547
Max Act: 2.2776. Min Act: -0.1700
Data Index: 1901359 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5547. Min Range: -2.5547
Max Act: 2.2941. Min Act: -0.1700
Data Index: 471345 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5547. Min Range: -2.5547
Max Act: 2.2446. Min Act: -0.1700
Data Index: 7133170 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5547. Min Range: -2.5547
Max Act: 2.2446. Min Act: -0.1700
Data Index: 2334318 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5547. Min Range: -2.5547
Max Act: 2.2611. Min Act: -0.1700
Data Index: 5776900 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5547. Min Range: -2.5547
Max Act: 2.2115. Min Act: -0.1700
Data Index: 3157477 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5547. Min Range: -2.5547
Max Act: 2.2280. Min Act: -0.1700
Data Index: 3270081 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5547. Min Range: -2.5547
Max Act: 2.2115. Min Act: -0.1700
Data Index: 2002750 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5547. Min Range: -2.5547
Max Act: 2.2280. Min Act: -0.1700
Data Index: 6716809 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5547. Min Range: -2.5547
Max Act: 2.2280. Min Act: -0.1700
Data Index: 2654926 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5547. Min Range: -2.5547
Max Act: 2.2115. Min Act: -0.1700
Data Index: 5018145 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5547. Min Range: -2.5547
Max Act: 2.2115. Min Act: -0.1700
Data Index: 5669716 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5547. Min Range: -2.5547
Max Act: 2.1949. Min Act: -0.1700
Data Index: 1250923 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5547. Min Range: -2.5547
Max Act: 2.1949. Min Act: -0.1700
Data Index: 4960277 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5547. Min Range: -2.5547
Max Act: 2.1949. Min Act: -0.1700
Data Index: 3904341 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19