Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5450 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6873. Min Range: -6.6873
Max Act: 6.6873. Min Act: -0.1700
Data Index: 3759702 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6873. Min Range: -6.6873
Max Act: 6.6248. Min Act: -0.1700
Data Index: 40380 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6873. Min Range: -6.6873
Max Act: 6.5623. Min Act: -0.1700
Data Index: 5933232 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6873. Min Range: -6.6873
Max Act: 6.5311. Min Act: -0.1700
Data Index: 6511963 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6873. Min Range: -6.6873
Max Act: 6.5623. Min Act: -0.1700
Data Index: 7460429 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6873. Min Range: -6.6873
Max Act: 6.4061. Min Act: -0.1700
Data Index: 7757539 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6873. Min Range: -6.6873
Max Act: 6.3748. Min Act: -0.1700
Data Index: 3073961 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6873. Min Range: -6.6873
Max Act: 6.3436. Min Act: -0.1700
Data Index: 8407241 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6873. Min Range: -6.6873
Max Act: 6.3436. Min Act: -0.1700
Data Index: 6361533 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6873. Min Range: -6.6873
Max Act: 6.3436. Min Act: -0.1700
Data Index: 8594419 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6873. Min Range: -6.6873
Max Act: 6.3436. Min Act: -0.1700
Data Index: 7603868 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6873. Min Range: -6.6873
Max Act: 6.3436. Min Act: -0.1700
Data Index: 2850180 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6873. Min Range: -6.6873
Max Act: 6.3123. Min Act: -0.1700
Data Index: 3945501 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6873. Min Range: -6.6873
Max Act: 6.3123. Min Act: -0.1700
Data Index: 7334244 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6873. Min Range: -6.6873
Max Act: 6.3123. Min Act: -0.1700
Data Index: 1177172 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6873. Min Range: -6.6873
Max Act: 6.2498. Min Act: -0.1700
Data Index: 5392394 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6873. Min Range: -6.6873
Max Act: 6.2811. Min Act: -0.1700
Data Index: 316641 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6873. Min Range: -6.6873
Max Act: 6.2811. Min Act: -0.1700
Data Index: 8130143 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6873. Min Range: -6.6873
Max Act: 6.2498. Min Act: -0.1700
Data Index: 3419065 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6873. Min Range: -6.6873
Max Act: 6.2186. Min Act: -0.1700
Data Index: 5155315 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19