Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4054 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7586. Min Range: -2.7586
Max Act: 2.7586. Min Act: -0.1700
Data Index: 1360735 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7586. Min Range: -2.7586
Max Act: 2.7267. Min Act: -0.1700
Data Index: 1213296 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7586. Min Range: -2.7586
Max Act: 2.7107. Min Act: -0.1700
Data Index: 4252446 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7586. Min Range: -2.7586
Max Act: 2.6626. Min Act: -0.1700
Data Index: 624278 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7586. Min Range: -2.7586
Max Act: 2.6466. Min Act: -0.1700
Data Index: 5364841 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7586. Min Range: -2.7586
Max Act: 2.6466. Min Act: -0.1700
Data Index: 6299475 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7586. Min Range: -2.7586
Max Act: 2.6305. Min Act: -0.1700
Data Index: 6477044 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7586. Min Range: -2.7586
Max Act: 2.6145. Min Act: -0.1700
Data Index: 5814191 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7586. Min Range: -2.7586
Max Act: 2.5984. Min Act: -0.1700
Data Index: 4113617 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7586. Min Range: -2.7586
Max Act: 2.6145. Min Act: -0.1700
Data Index: 3698827 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7586. Min Range: -2.7586
Max Act: 2.6145. Min Act: -0.1700
Data Index: 1241452 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7586. Min Range: -2.7586
Max Act: 2.5823. Min Act: -0.1700
Data Index: 5517531 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7586. Min Range: -2.7586
Max Act: 2.5823. Min Act: -0.1700
Data Index: 6907024 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7586. Min Range: -2.7586
Max Act: 2.5662. Min Act: -0.1700
Data Index: 7282018 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7586. Min Range: -2.7586
Max Act: 2.5823. Min Act: -0.1700
Data Index: 7280176 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7586. Min Range: -2.7586
Max Act: 2.5823. Min Act: -0.1700
Data Index: 5323653 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7586. Min Range: -2.7586
Max Act: 2.5662. Min Act: -0.1700
Data Index: 977037 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7586. Min Range: -2.7586
Max Act: 2.5662. Min Act: -0.1700
Data Index: 1887636 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7586. Min Range: -2.7586
Max Act: 2.5662. Min Act: -0.1700
Data Index: 4225944 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7586. Min Range: -2.7586
Max Act: 2.5662. Min Act: -0.1700
Data Index: 3618686 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19