Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 957 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.4494. Min Act: -0.1700
Data Index: 4790946 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.4182. Min Act: -0.1700
Data Index: 3746890 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.3869. Min Act: -0.1700
Data Index: 7241198 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.3869. Min Act: -0.1700
Data Index: 3095260 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.3869. Min Act: -0.1700
Data Index: 8532868 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.3557. Min Act: -0.1700
Data Index: 5170736 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.3557. Min Act: -0.1700
Data Index: 4342652 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.3557. Min Act: -0.1700
Data Index: 4485751 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.3557. Min Act: -0.1700
Data Index: 3264651 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.3557. Min Act: -0.1700
Data Index: 7585475 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.3244. Min Act: -0.1700
Data Index: 6240358 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.2307. Min Act: -0.1700
Data Index: 1309887 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.2307. Min Act: -0.1700
Data Index: 8589878 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.2307. Min Act: -0.1700
Data Index: 3344131 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.2307. Min Act: -0.1700
Data Index: 8654873 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.2307. Min Act: -0.1700
Data Index: 7180398 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.1994. Min Act: -0.1700
Data Index: 6249598 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.1994. Min Act: -0.1700
Data Index: 1867899 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.1994. Min Act: -0.1700
Data Index: 4543213 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4494. Min Range: -4.4494
Max Act: 4.1994. Min Act: -0.1700
Data Index: 693601 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19