Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1524 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8179. Min Range: -6.8179
Max Act: 6.8179. Min Act: -0.1700
Data Index: 1671956 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8179. Min Range: -6.8179
Max Act: 6.6929. Min Act: -0.1700
Data Index: 6242132 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8179. Min Range: -6.8179
Max Act: 6.5679. Min Act: -0.1700
Data Index: 7406467 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8179. Min Range: -6.8179
Max Act: 6.5366. Min Act: -0.1700
Data Index: 8596259 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8179. Min Range: -6.8179
Max Act: 6.5054. Min Act: -0.1700
Data Index: 3108641 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8179. Min Range: -6.8179
Max Act: 6.5054. Min Act: -0.1700
Data Index: 5455033 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8179. Min Range: -6.8179
Max Act: 6.4741. Min Act: -0.1700
Data Index: 2785964 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8179. Min Range: -6.8179
Max Act: 6.4429. Min Act: -0.1700
Data Index: 8357172 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8179. Min Range: -6.8179
Max Act: 6.4116. Min Act: -0.1700
Data Index: 1474854 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8179. Min Range: -6.8179
Max Act: 6.4116. Min Act: -0.1700
Data Index: 8649331 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8179. Min Range: -6.8179
Max Act: 6.4116. Min Act: -0.1700
Data Index: 5640133 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8179. Min Range: -6.8179
Max Act: 6.2866. Min Act: -0.1700
Data Index: 3265506 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8179. Min Range: -6.8179
Max Act: 6.2866. Min Act: -0.1700
Data Index: 8814550 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8179. Min Range: -6.8179
Max Act: 6.2866. Min Act: -0.1700
Data Index: 1761343 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8179. Min Range: -6.8179
Max Act: 6.2241. Min Act: -0.1700
Data Index: 6272009 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8179. Min Range: -6.8179
Max Act: 6.2554. Min Act: -0.1700
Data Index: 7812723 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8179. Min Range: -6.8179
Max Act: 6.2241. Min Act: -0.1700
Data Index: 7128837 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8179. Min Range: -6.8179
Max Act: 6.2241. Min Act: -0.1700
Data Index: 4934 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8179. Min Range: -6.8179
Max Act: 6.1929. Min Act: -0.1700
Data Index: 241655 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8179. Min Range: -6.8179
Max Act: 6.1929. Min Act: -0.1700
Data Index: 3090259 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19