Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1540 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4550. Min Range: -4.4550
Max Act: 4.4550. Min Act: -0.1700
Data Index: 8297707 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4550. Min Range: -4.4550
Max Act: 4.2988. Min Act: -0.1700
Data Index: 6622000 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4550. Min Range: -4.4550
Max Act: 4.2675. Min Act: -0.1700
Data Index: 8759272 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4550. Min Range: -4.4550
Max Act: 4.2050. Min Act: -0.1700
Data Index: 8117341 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4550. Min Range: -4.4550
Max Act: 4.1425. Min Act: -0.1700
Data Index: 1700148 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4550. Min Range: -4.4550
Max Act: 4.1425. Min Act: -0.1700
Data Index: 1593958 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4550. Min Range: -4.4550
Max Act: 4.1425. Min Act: -0.1700
Data Index: 3705612 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4550. Min Range: -4.4550
Max Act: 4.1425. Min Act: -0.1700
Data Index: 6072278 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4550. Min Range: -4.4550
Max Act: 4.1113. Min Act: -0.1700
Data Index: 4086778 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4550. Min Range: -4.4550
Max Act: 4.1113. Min Act: -0.1700
Data Index: 8661438 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4550. Min Range: -4.4550
Max Act: 4.1113. Min Act: -0.1700
Data Index: 4086781 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4550. Min Range: -4.4550
Max Act: 4.0487. Min Act: -0.1700
Data Index: 5001280 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4550. Min Range: -4.4550
Max Act: 4.0175. Min Act: -0.1700
Data Index: 8080754 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4550. Min Range: -4.4550
Max Act: 3.9862. Min Act: -0.1700
Data Index: 5016235 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4550. Min Range: -4.4550
Max Act: 3.9862. Min Act: -0.1700
Data Index: 5182965 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4550. Min Range: -4.4550
Max Act: 3.9862. Min Act: -0.1700
Data Index: 6696367 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4550. Min Range: -4.4550
Max Act: 3.9862. Min Act: -0.1700
Data Index: 200624 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4550. Min Range: -4.4550
Max Act: 3.9862. Min Act: -0.1700
Data Index: 4291359 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4550. Min Range: -4.4550
Max Act: 3.9862. Min Act: -0.1700
Data Index: 2337566 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4550. Min Range: -4.4550
Max Act: 3.9862. Min Act: -0.1700
Data Index: 4595044 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19