Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1310 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7726. Min Range: -3.7726
Max Act: 3.7726. Min Act: -0.1700
Data Index: 6470462 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7726. Min Range: -3.7726
Max Act: 3.7570. Min Act: -0.1700
Data Index: 4238213 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7726. Min Range: -3.7726
Max Act: 3.7413. Min Act: -0.1700
Data Index: 7415224 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7726. Min Range: -3.7726
Max Act: 3.7100. Min Act: -0.1700
Data Index: 8380681 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7726. Min Range: -3.7726
Max Act: 3.6631. Min Act: -0.1700
Data Index: 3513672 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7726. Min Range: -3.7726
Max Act: 3.6788. Min Act: -0.1700
Data Index: 5487961 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7726. Min Range: -3.7726
Max Act: 3.6318. Min Act: -0.1700
Data Index: 840644 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7726. Min Range: -3.7726
Max Act: 3.6475. Min Act: -0.1700
Data Index: 7022945 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7726. Min Range: -3.7726
Max Act: 3.6631. Min Act: -0.1700
Data Index: 8770385 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7726. Min Range: -3.7726
Max Act: 3.6162. Min Act: -0.1700
Data Index: 3362325 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7726. Min Range: -3.7726
Max Act: 3.6162. Min Act: -0.1700
Data Index: 6925923 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7726. Min Range: -3.7726
Max Act: 3.6162. Min Act: -0.1700
Data Index: 8644997 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7726. Min Range: -3.7726
Max Act: 3.6005. Min Act: -0.1700
Data Index: 6070919 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7726. Min Range: -3.7726
Max Act: 3.5849. Min Act: -0.1700
Data Index: 8563577 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7726. Min Range: -3.7726
Max Act: 3.6162. Min Act: -0.1700
Data Index: 7697917 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7726. Min Range: -3.7726
Max Act: 3.5849. Min Act: -0.1700
Data Index: 4386983 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7726. Min Range: -3.7726
Max Act: 3.6005. Min Act: -0.1700
Data Index: 5994023 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7726. Min Range: -3.7726
Max Act: 3.6005. Min Act: -0.1700
Data Index: 4921132 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7726. Min Range: -3.7726
Max Act: 3.5849. Min Act: -0.1700
Data Index: 5865153 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7726. Min Range: -3.7726
Max Act: 3.5692. Min Act: -0.1700
Data Index: 6904954 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19