Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 719 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.8862. Min Act: -0.1700
Data Index: 4277033 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.7298. Min Act: -0.1700
Data Index: 4595244 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.6829. Min Act: -0.1700
Data Index: 5879484 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.6829. Min Act: -0.1700
Data Index: 2837046 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.6359. Min Act: -0.1700
Data Index: 5632364 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.5890. Min Act: -0.1700
Data Index: 7462858 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.5733. Min Act: -0.1700
Data Index: 6706635 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.5420. Min Act: -0.1700
Data Index: 3227499 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.5577. Min Act: -0.1700
Data Index: 7644376 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.5420. Min Act: -0.1700
Data Index: 4897195 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.5420. Min Act: -0.1700
Data Index: 8281349 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.5107. Min Act: -0.1700
Data Index: 4255640 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.4950. Min Act: -0.1700
Data Index: 6626888 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.4950. Min Act: -0.1700
Data Index: 2466324 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.4794. Min Act: -0.1700
Data Index: 7645572 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.4794. Min Act: -0.1700
Data Index: 3078408 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.4637. Min Act: -0.1700
Data Index: 8356839 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.4794. Min Act: -0.1700
Data Index: 896009 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.4480. Min Act: -0.1700
Data Index: 6343125 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.4480. Min Act: -0.1700
Data Index: 3062130 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19