Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2794 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5545. Min Range: -6.5545
Max Act: 6.5545. Min Act: -0.1700
Data Index: 1381383 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5545. Min Range: -6.5545
Max Act: 6.4295. Min Act: -0.1700
Data Index: 895336 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5545. Min Range: -6.5545
Max Act: 6.4295. Min Act: -0.1700
Data Index: 2372452 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5545. Min Range: -6.5545
Max Act: 6.3983. Min Act: -0.1700
Data Index: 3271572 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5545. Min Range: -6.5545
Max Act: 6.3358. Min Act: -0.1700
Data Index: 5856331 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5545. Min Range: -6.5545
Max Act: 6.3045. Min Act: -0.1700
Data Index: 6684270 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5545. Min Range: -6.5545
Max Act: 6.3358. Min Act: -0.1700
Data Index: 8213536 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5545. Min Range: -6.5545
Max Act: 6.2733. Min Act: -0.1700
Data Index: 3142498 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5545. Min Range: -6.5545
Max Act: 6.2733. Min Act: -0.1698
Data Index: 6640254 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5545. Min Range: -6.5545
Max Act: 6.2733. Min Act: -0.1700
Data Index: 5898837 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5545. Min Range: -6.5545
Max Act: 6.2420. Min Act: -0.1700
Data Index: 1381382 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5545. Min Range: -6.5545
Max Act: 6.2420. Min Act: -0.1700
Data Index: 4089554 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5545. Min Range: -6.5545
Max Act: 6.2420. Min Act: -0.1700
Data Index: 1068790 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5545. Min Range: -6.5545
Max Act: 6.2108. Min Act: -0.1700
Data Index: 2639705 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5545. Min Range: -6.5545
Max Act: 6.2420. Min Act: -0.1700
Data Index: 6689520 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5545. Min Range: -6.5545
Max Act: 6.2420. Min Act: -0.1700
Data Index: 8740102 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5545. Min Range: -6.5545
Max Act: 6.1795. Min Act: -0.1700
Data Index: 1385695 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5545. Min Range: -6.5545
Max Act: 6.1795. Min Act: -0.1700
Data Index: 3819236 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5545. Min Range: -6.5545
Max Act: 6.1795. Min Act: -0.1700
Data Index: 4906600 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5545. Min Range: -6.5545
Max Act: 6.1483. Min Act: -0.1700
Data Index: 6604267 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19