Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 278 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3933. Min Range: -6.3933
Max Act: 6.3933. Min Act: -0.1700
Data Index: 7797318 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3933. Min Range: -6.3933
Max Act: 6.2058. Min Act: -0.1700
Data Index: 848721 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3933. Min Range: -6.3933
Max Act: 6.2995. Min Act: -0.1700
Data Index: 5755405 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3933. Min Range: -6.3933
Max Act: 6.1745. Min Act: -0.1700
Data Index: 25694 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3933. Min Range: -6.3933
Max Act: 6.0808. Min Act: -0.1700
Data Index: 6071537 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3933. Min Range: -6.3933
Max Act: 6.0495. Min Act: -0.1700
Data Index: 4214437 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3933. Min Range: -6.3933
Max Act: 6.1120. Min Act: -0.1700
Data Index: 6107133 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3933. Min Range: -6.3933
Max Act: 6.0495. Min Act: -0.1700
Data Index: 133646 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3933. Min Range: -6.3933
Max Act: 6.0808. Min Act: -0.1700
Data Index: 2213209 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3933. Min Range: -6.3933
Max Act: 6.0808. Min Act: -0.1700
Data Index: 7468411 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3933. Min Range: -6.3933
Max Act: 6.0183. Min Act: -0.1700
Data Index: 7783607 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3933. Min Range: -6.3933
Max Act: 5.9558. Min Act: -0.1700
Data Index: 7296654 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3933. Min Range: -6.3933
Max Act: 5.9870. Min Act: -0.1700
Data Index: 1959441 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3933. Min Range: -6.3933
Max Act: 5.9245. Min Act: -0.1700
Data Index: 133647 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3933. Min Range: -6.3933
Max Act: 5.9558. Min Act: -0.1700
Data Index: 6232182 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3933. Min Range: -6.3933
Max Act: 5.8933. Min Act: -0.1700
Data Index: 8750402 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3933. Min Range: -6.3933
Max Act: 5.8933. Min Act: -0.1700
Data Index: 7367041 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3933. Min Range: -6.3933
Max Act: 5.8933. Min Act: -0.1700
Data Index: 6991858 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3933. Min Range: -6.3933
Max Act: 5.8620. Min Act: -0.1700
Data Index: 2802813 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3933. Min Range: -6.3933
Max Act: 5.8620. Min Act: -0.1700
Data Index: 1331981 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19