Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3386 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4179. Min Range: -5.4179
Max Act: 5.4179. Min Act: -0.1700
Data Index: 5359103 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4179. Min Range: -5.4179
Max Act: 5.3242. Min Act: -0.1700
Data Index: 3394044 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4179. Min Range: -5.4179
Max Act: 5.2617. Min Act: -0.1700
Data Index: 1026967 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4179. Min Range: -5.4179
Max Act: 5.2304. Min Act: -0.1700
Data Index: 5056578 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4179. Min Range: -5.4179
Max Act: 5.2617. Min Act: -0.1700
Data Index: 5056579 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4179. Min Range: -5.4179
Max Act: 5.1992. Min Act: -0.1700
Data Index: 2427233 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4179. Min Range: -5.4179
Max Act: 5.1679. Min Act: -0.1700
Data Index: 8139717 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4179. Min Range: -5.4179
Max Act: 5.1679. Min Act: -0.1700
Data Index: 2703406 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4179. Min Range: -5.4179
Max Act: 5.1679. Min Act: -0.1700
Data Index: 2078774 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4179. Min Range: -5.4179
Max Act: 5.1679. Min Act: -0.1700
Data Index: 801104 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4179. Min Range: -5.4179
Max Act: 5.1054. Min Act: -0.1700
Data Index: 5133068 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4179. Min Range: -5.4179
Max Act: 5.1054. Min Act: -0.1700
Data Index: 6473089 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4179. Min Range: -5.4179
Max Act: 5.1054. Min Act: -0.1700
Data Index: 5056577 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4179. Min Range: -5.4179
Max Act: 5.0429. Min Act: -0.1700
Data Index: 4689114 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4179. Min Range: -5.4179
Max Act: 5.0429. Min Act: -0.1700
Data Index: 6396830 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4179. Min Range: -5.4179
Max Act: 5.0429. Min Act: -0.1700
Data Index: 8574657 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4179. Min Range: -5.4179
Max Act: 5.0117. Min Act: -0.1700
Data Index: 6473168 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4179. Min Range: -5.4179
Max Act: 5.0117. Min Act: -0.1700
Data Index: 1445216 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4179. Min Range: -5.4179
Max Act: 5.0117. Min Act: -0.1700
Data Index: 2237987 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4179. Min Range: -5.4179
Max Act: 5.0429. Min Act: -0.1700
Data Index: 5130021 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19