Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3000 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.4307. Min Act: -0.1700
Data Index: 6700612 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.3995. Min Act: -0.1700
Data Index: 7646167 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.3682. Min Act: -0.1700
Data Index: 181058 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.3370. Min Act: -0.1700
Data Index: 269681 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.3995. Min Act: -0.1700
Data Index: 5629320 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.3370. Min Act: -0.1700
Data Index: 3740656 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.3057. Min Act: -0.1700
Data Index: 2284232 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.3057. Min Act: -0.1700
Data Index: 3100266 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.2745. Min Act: -0.1700
Data Index: 6812188 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.2745. Min Act: -0.1700
Data Index: 3902248 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.2745. Min Act: -0.1700
Data Index: 6653328 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.3057. Min Act: -0.1700
Data Index: 6283574 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.3057. Min Act: -0.1700
Data Index: 8769729 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.2432. Min Act: -0.1700
Data Index: 3878863 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.2432. Min Act: -0.1700
Data Index: 6166963 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.2745. Min Act: -0.1700
Data Index: 3902250 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.2745. Min Act: -0.1700
Data Index: 6755253 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.2432. Min Act: -0.1700
Data Index: 4927515 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.2120. Min Act: -0.1700
Data Index: 2292166 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.2745. Min Act: -0.1700
Data Index: 382394 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19