Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 13 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0808. Min Range: -5.0808
Max Act: 5.0808. Min Act: -0.1700
Data Index: 7212293 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0808. Min Range: -5.0808
Max Act: 5.0183. Min Act: -0.1700
Data Index: 6344180 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0808. Min Range: -5.0808
Max Act: 5.0183. Min Act: -0.1700
Data Index: 2987223 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.8933. Min Act: -0.1700
Data Index: 2704187 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.8620. Min Act: -0.1700
Data Index: 6539727 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.8933. Min Act: -0.1700
Data Index: 7574314 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.8308. Min Act: -0.1700
Data Index: 2145224 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.7995. Min Act: -0.1700
Data Index: 6951011 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.7995. Min Act: -0.1700
Data Index: 7843078 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.7995. Min Act: -0.1700
Data Index: 6463335 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.7995. Min Act: -0.1700
Data Index: 6539724 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.7683. Min Act: -0.1700
Data Index: 8656721 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.7683. Min Act: -0.1700
Data Index: 1530670 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.7683. Min Act: -0.1700
Data Index: 5554548 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.7683. Min Act: -0.1700
Data Index: 1429599 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.7683. Min Act: -0.1700
Data Index: 8575621 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.7995. Min Act: -0.1700
Data Index: 2145225 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.7370. Min Act: -0.1700
Data Index: 3624555 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.7370. Min Act: -0.1700
Data Index: 3815084 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.7370. Min Act: -0.1700
Data Index: 7209080 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19