Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1771 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0487. Min Range: -2.0487
Max Act: 2.0487. Min Act: -0.1700
Data Index: 2527929 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0487. Min Range: -2.0487
Max Act: 1.9981. Min Act: -0.1700
Data Index: 7248327 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0487. Min Range: -2.0487
Max Act: 1.9388. Min Act: -0.1700
Data Index: 5478136 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0487. Min Range: -2.0487
Max Act: 1.8791. Min Act: -0.1700
Data Index: 1606222 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0487. Min Range: -2.0487
Max Act: 1.9218. Min Act: -0.1700
Data Index: 1073033 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0487. Min Range: -2.0487
Max Act: 1.8962. Min Act: -0.1700
Data Index: 421099 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0487. Min Range: -2.0487
Max Act: 1.9047. Min Act: -0.1700
Data Index: 3632959 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0487. Min Range: -2.0487
Max Act: 1.8962. Min Act: -0.1700
Data Index: 5545620 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0487. Min Range: -2.0487
Max Act: 1.8791. Min Act: -0.1700
Data Index: 2104008 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0487. Min Range: -2.0487
Max Act: 1.8620. Min Act: -0.1700
Data Index: 957145 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0487. Min Range: -2.0487
Max Act: 1.8535. Min Act: -0.1700
Data Index: 6226744 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0487. Min Range: -2.0487
Max Act: 1.8620. Min Act: -0.1700
Data Index: 4661182 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0487. Min Range: -2.0487
Max Act: 1.9047. Min Act: -0.1700
Data Index: 1801373 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0487. Min Range: -2.0487
Max Act: 1.8877. Min Act: -0.1700
Data Index: 7062089 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0487. Min Range: -2.0487
Max Act: 1.8620. Min Act: -0.1700
Data Index: 1587010 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0487. Min Range: -2.0487
Max Act: 1.8364. Min Act: -0.1700
Data Index: 1393262 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0487. Min Range: -2.0487
Max Act: 1.8791. Min Act: -0.1700
Data Index: 5804923 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0487. Min Range: -2.0487
Max Act: 1.8535. Min Act: -0.1700
Data Index: 2131943 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0487. Min Range: -2.0487
Max Act: 1.8449. Min Act: -0.1700
Data Index: 5260640 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0487. Min Range: -2.0487
Max Act: 1.8364. Min Act: -0.1700
Data Index: 6910083 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19