Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2518 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2043. Min Range: -5.2043
Max Act: 5.2043. Min Act: -0.1700
Data Index: 3347301 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2043. Min Range: -5.2043
Max Act: 4.7043. Min Act: -0.1700
Data Index: 5148254 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2043. Min Range: -5.2043
Max Act: 4.6730. Min Act: -0.1700
Data Index: 877132 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2043. Min Range: -5.2043
Max Act: 4.5168. Min Act: -0.1700
Data Index: 7793945 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2043. Min Range: -5.2043
Max Act: 4.4855. Min Act: -0.1700
Data Index: 7352221 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2043. Min Range: -5.2043
Max Act: 4.4855. Min Act: -0.1700
Data Index: 5766463 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2043. Min Range: -5.2043
Max Act: 4.4855. Min Act: -0.1700
Data Index: 2622340 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2043. Min Range: -5.2043
Max Act: 4.4230. Min Act: -0.1700
Data Index: 1826635 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2043. Min Range: -5.2043
Max Act: 4.4542. Min Act: -0.1700
Data Index: 4591494 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2043. Min Range: -5.2043
Max Act: 4.4542. Min Act: -0.1700
Data Index: 7785577 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2043. Min Range: -5.2043
Max Act: 4.4855. Min Act: -0.1700
Data Index: 8770586 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2043. Min Range: -5.2043
Max Act: 4.4230. Min Act: -0.1700
Data Index: 4519139 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2043. Min Range: -5.2043
Max Act: 4.4230. Min Act: -0.1700
Data Index: 4796491 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2043. Min Range: -5.2043
Max Act: 4.4230. Min Act: -0.1700
Data Index: 7114261 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2043. Min Range: -5.2043
Max Act: 4.3605. Min Act: -0.1700
Data Index: 3444851 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2043. Min Range: -5.2043
Max Act: 4.3917. Min Act: -0.1700
Data Index: 4557457 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2043. Min Range: -5.2043
Max Act: 4.3605. Min Act: -0.1700
Data Index: 2429722 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2043. Min Range: -5.2043
Max Act: 4.3917. Min Act: -0.1700
Data Index: 5449713 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2043. Min Range: -5.2043
Max Act: 4.3605. Min Act: -0.1700
Data Index: 7803089 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2043. Min Range: -5.2043
Max Act: 4.3605. Min Act: -0.1700
Data Index: 119201 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19