Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4040 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0546. Min Range: -4.0546
Max Act: 4.0233. Min Act: -0.1700
Data Index: 5333675 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0546. Min Range: -4.0546
Max Act: 4.0546. Min Act: -0.1700
Data Index: 5902932 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0546. Min Range: -4.0546
Max Act: 4.0546. Min Act: -0.1700
Data Index: 321478 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0546. Min Range: -4.0546
Max Act: 4.0546. Min Act: -0.1700
Data Index: 7313666 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0546. Min Range: -4.0546
Max Act: 3.9608. Min Act: -0.1700
Data Index: 5007044 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0546. Min Range: -4.0546
Max Act: 3.9608. Min Act: -0.1700
Data Index: 2087911 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0546. Min Range: -4.0546
Max Act: 3.9296. Min Act: -0.1700
Data Index: 2546318 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0546. Min Range: -4.0546
Max Act: 3.9296. Min Act: -0.1700
Data Index: 4799469 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0546. Min Range: -4.0546
Max Act: 3.9296. Min Act: -0.1700
Data Index: 4462198 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0546. Min Range: -4.0546
Max Act: 3.8983. Min Act: -0.1700
Data Index: 5131055 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0546. Min Range: -4.0546
Max Act: 3.9296. Min Act: -0.1700
Data Index: 6528960 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0546. Min Range: -4.0546
Max Act: 3.8983. Min Act: -0.1700
Data Index: 114849 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0546. Min Range: -4.0546
Max Act: 3.8983. Min Act: -0.1700
Data Index: 7770471 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0546. Min Range: -4.0546
Max Act: 3.8983. Min Act: -0.1700
Data Index: 8100522 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0546. Min Range: -4.0546
Max Act: 3.8670. Min Act: -0.1700
Data Index: 4232211 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0546. Min Range: -4.0546
Max Act: 3.8670. Min Act: -0.1700
Data Index: 4292263 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0546. Min Range: -4.0546
Max Act: 3.8670. Min Act: -0.1700
Data Index: 4203968 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0546. Min Range: -4.0546
Max Act: 3.8670. Min Act: -0.1700
Data Index: 4497381 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0546. Min Range: -4.0546
Max Act: 3.8670. Min Act: -0.1700
Data Index: 5626128 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0546. Min Range: -4.0546
Max Act: 3.8670. Min Act: -0.1700
Data Index: 5772196 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19